© 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. 112978
    Prev
    Next
    INDEX
    Explanations

    Sar

    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
     of
    -0.07
    anic
    -0.07
     Nest
    -0.07
     Laundry
    -0.07
    ителей
    -0.07
    分级
    -0.07
    Hide
    -0.06
    悠悠
    -0.06
     blush
    -0.06
    activo
    -0.06
    POSITIVE LOGITS
    _card
    0.08
     ???
    0.07
     Sociology
    0.07
     ramifications
    0.07
     partic
    0.07
     sar
    0.07
    龋
    0.07
     Россий
    0.07
     slated
    0.07
     بالن
    0.07
    Activations Density 0.012%

    No Known Activations