© 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. 111938
    Prev
    Next
    INDEX
    Explanations

    cars, especially convertibles

    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
    ridge
    -0.07
    USD
    -0.07
    getStyle
    -0.07
    orage
    -0.07
    .CONTENT
    -0.06
     governor
    -0.06
    外交
    -0.06
     baseball
    -0.06
    ounsel
    -0.06
    modifier
    -0.06
    POSITIVE LOGITS
    _front
    0.07
    簏
    0.07
    _remaining
    0.06
    联手
    0.06
     decryption
    0.06
    嫭
    0.06
    BitFields
    0.06
    NSURLSession
    0.06
    前十
    0.06
    _domains
    0.06
    Activations Density 0.015%

    No Known Activations