© 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. 121357
    Prev
    Next
    INDEX
    Explanations

    0

    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_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
     nicely
    -0.09
     neatly
    -0.08
    تحسين
    -0.07
     rebuilding
    -0.07
     Drinking
    -0.07
     ninth
    -0.07
     Building
    -0.07
     Cheat
    -0.07
    拧
    -0.07
    恨
    -0.07
    POSITIVE LOGITS
    *,
    0.09
    
    0.07
    bla
    0.07
     maxi
    0.07
    *
    0.07
    ｏ
    0.06
    ably
    0.06
    똬
    0.06
     ')
    0.06
    manız
    0.06
    Activations Density 0.023%

    No Known Activations