© 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. 11-RESID-POST-AA
    11. 74795
    Prev
    Next
    INDEX
    Explanations

    reference markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     документов
    -0.07
     SCE
    -0.07
     committee
    -0.07
     Strike
    -0.06
    :text
    -0.06
    /package
    -0.06
     uber
    -0.06
    “What
    -0.06
    /video
    -0.06
    	super
    -0.06
    POSITIVE LOGITS
    איר
    0.08
     hatred
    0.08
    ersed
    0.08
    _INST
    0.07
     Impro
    0.07
    更低
    0.07
     muttered
    0.07
    scaling
    0.07
    .lex
    0.07
    向外
    0.07
    Activations Density 0.001%

    No Known Activations