© 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. 60573
    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
    geber
    -0.08
     cupid
    -0.08
     removeFromSuperview
    -0.07
    看病
    -0.07
     الج
    -0.07
    岠
    -0.07
    אמין
    -0.07
    만
    -0.07
     sprzedaży
    -0.07
     update
    -0.07
    POSITIVE LOGITS
    conc
    0.07
     Archer
    0.07
     Leah
    0.07
    blog
    0.07
    _choice
    0.07
     Emma
    0.06
     eas
    0.06
    phrase
    0.06
     posts
    0.06
    法令
    0.06
    Activations Density 0.165%

    No Known Activations