© 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. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30011
    Prev
    Next
    INDEX
    Explanations

    code/mathematical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tant
    -0.31
    èĽĽ
    -0.27
    åijĬè¯ī大家
    -0.26
    COVER
    -0.26
    éĿ¢
    -0.26
    ä¸ŃåĽ½å¸Ĥåľº
    -0.25
    äºĴåĬ©
    -0.25
    .MediaType
    -0.25
    _SURFACE
    -0.25
     verk
    -0.24
    POSITIVE LOGITS
     identities
    0.26
    profiles
    0.26
    abilities
    0.25
    西çľģ
    0.25
     subscript
    0.24
     independ
    0.24
     profiles
    0.24
     Gül
    0.24
     strains
    0.24
     dramatically
    0.24
    Activations Density 2.567%

    No Known Activations