© 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. 76336
    Prev
    Next
    INDEX
    Explanations

    from

    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
    gree
    -0.07
     excluded
    -0.07
     Jar
    -0.06
    //----------------------------------------------------------------------------↵
    -0.06
    (/[
    -0.06
    靰
    -0.06
    搪
    -0.06
    𬭳
    -0.06
    agal
    -0.06
     respiratory
    -0.06
    POSITIVE LOGITS
    acts
    0.08
    SEG
    0.07
    ма
    0.07
    attacks
    0.07
    Monad
    0.07
     כפי
    0.07
    water
    0.07
    _Window
    0.07
    incy
    0.07
     looph
    0.07
    Activations Density 0.001%

    No Known Activations