© 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
    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. 26605
    Prev
    Next
    INDEX
    Explanations

    generated code

    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
     Katie
    -0.07
     racial
    -0.07
    陸
    -0.07
     Warn
    -0.07
    年之久
    -0.07
    (IOException
    -0.07
    são
    -0.07
     Ted
    -0.07
     samp
    -0.07
    陈
    -0.06
    POSITIVE LOGITS
    ęż
    0.07
    创新驱动
    0.07
    됨
    0.07
    стер
    0.07
    .Mapping
    0.06
    şa
    0.06
    oğlu
    0.06
     %[
    0.06
    Detach
    0.06
    watch
    0.06
    Activations Density 0.012%

    No Known Activations