© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 117257
    Prev
    Next
    INDEX
    Explanations

    Empty

    np_max-act · gemini-2.0-flash

    programming-related identifiers and artifacts, especially snake_case field names, config keys, include/import paths, acronyms, and build/log tokens.

    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
    מחר
    -0.07
    🠳
    -0.07
     miễn
    -0.07
    esper
    -0.07
     последние
    -0.06
     Vertex
    -0.06
     Petroleum
    -0.06
    trib
    -0.06
     swore
    -0.06
     вмест
    -0.06
    POSITIVE LOGITS
     FullName
    0.08
     GroupLayout
    0.07
    /WebAPI
    0.07
    BOOLEAN
    0.07
    未来发展
    0.07
    ysqli
    0.07
    ####↵
    0.07
     elegance
    0.07
     Shaun
    0.07
    经济增长
    0.07
    Activations Density 0.411%

    No Known Activations