© 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. 23-TRANSCODER-HP
    7. 25026
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CCC
    -0.28
    家ä½ı
    -0.25
     CType
    -0.25
    æł¡
    -0.24
    PF
    -0.24
    家åħ¬åı¸
    -0.24
    oux
    -0.24
    iris
    -0.24
    Portal
    -0.24
    Annual
    -0.23
    POSITIVE LOGITS
    çļĦç¨ĭ度
    0.28
    èµ·æĿ¥
    0.27
     Liber
    0.27
    åĩºæĿ¥
    0.26
    lib
    0.26
     alternatives
    0.26
     giving
    0.25
     pred
    0.25
     incorporating
    0.25
    [out
    0.25
    Activations Density 0.005%

    No Known Activations