© 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 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. 19-RESID-POST-AA
    11. 70493
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingredient
    -0.07
     include
    -0.06
     сф
    -0.06
    -range
    -0.06
    جر
    -0.06
     Eric
    -0.06
    有个
    -0.06
    尽快
    -0.06
     cram
    -0.06
     Eternal
    -0.06
    POSITIVE LOGITS
    outing
    0.09
    少数民族
    0.07
    رات
    0.07
    OUNTRY
    0.06
    anded
    0.06
    本场比赛
    0.06
    ydı
    0.06
    byname
    0.06
    的支持
    0.06
    World
    0.06
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.