© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 90215
    Prev
    Next
    INDEX
    Explanations

    Ying/ing

    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
    午
    -0.07
    neapolis
    -0.07
    �
    -0.07
    importDefault
    -0.07
    ╠
    -0.07
    .fromFunction
    -0.07
    _not
    -0.07
     giận
    -0.07
    _RETURNTRANSFER
    -0.06
     lesb
    -0.06
    POSITIVE LOGITS
     trades
    0.08
     thánh
    0.07
    \Services
    0.07
     advertising
    0.07
     ofs
    0.07
    INET
    0.07
    阴阳
    0.07
    ammed
    0.07
     Scotch
    0.07
     Wordpress
    0.07
    Activations Density 0.011%

    No Known Activations