© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 45847
    Prev
    Next
    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash

    clausal connectors and high-frequency function words that signal explanation, causation, emphasis, or linkage between ideas, often across languages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     готов
    -0.08
     Typically
    -0.08
     effectively
    -0.07
     weighs
    -0.07
     deviation
    -0.07
    Completed
    -0.07
    .Executor
    -0.07
     Convers
    -0.07
    加重
    -0.07
     independently
    -0.07
    POSITIVE LOGITS
                                 ↵
    0.08
    رابط
    0.08
     }\
    0.08
    brown
    0.07
    ,.
    0.07
     ARC
    0.07
    atures
    0.07
    崖
    0.07
    CTRL
    0.07
    	H
    0.07
    Activations Density 0.854%

    No Known Activations