© 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. 15-RESID-POST-AA
    11. 60553
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouser
    -0.10
     COURT
    -0.07
     tanker
    -0.07
    ادر
    -0.07
    -now
    -0.07
    hänge
    -0.06
    ！');↵
    -0.06
    منتجات
    -0.06
     Physics
    -0.06
    考场
    -0.06
    POSITIVE LOGITS
     Санкт
    0.07
     Hyderabad
    0.07
     Vegetable
    0.07
    一段时间
    0.07
    .Black
    0.07
    .Trim
    0.07
    本轮
    0.07
     owns
    0.07
    喝
    0.07
    真实的
    0.07
    Activations Density 0.121%

    No Known Activations