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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 68035
    Prev
    Next
    INDEX
    Explanations

    int

    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
     Stand
    -0.07
     essential
    -0.07
    .tag
    -0.07
     Penalty
    -0.07
    stalk
    -0.07
    /fr
    -0.07
    Ga
    -0.07
    王子
    -0.07
    hop
    -0.07
     ngx
    -0.06
    POSITIVE LOGITS
    ertype
    0.07
    steel
    0.07
    לס
    0.07
    ﺕ
    0.06
    =post
    0.06
    踉
    0.06
     quat
    0.06
    -dollar
    0.06
    二手
    0.06
    ransition
    0.06
    Activations Density 0.002%

    No Known Activations