© 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. 118702
    Prev
    Next
    INDEX
    Explanations

    cipher

    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
    酢
    -0.07
     NEO
    -0.07
    vet
    -0.07
     OBJECT
    -0.07
    组团
    -0.07
     �
    -0.07
    uel
    -0.07
     Nutrition
    -0.07
    blade
    -0.07
    Database
    -0.07
    POSITIVE LOGITS
     cipher
    0.08
    \Category
    0.07
    .comm
    0.07
    .commons
    0.07
     shaving
    0.07
    人工智能
    0.07
     suff
    0.06
    (fil
    0.06
     Louisville
    0.06
     haciendo
    0.06
    Activations Density 0.003%

    No Known Activations