© 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. 19-TRANSCODER-HP
    7. 8277
    Prev
    Next
    INDEX
    Explanations

    searching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Łå¸ĮæľĽ
    -0.29
    leness
    -0.28
    ä¹Łåı¯èĥ½
    -0.28
    ä¹Łèĥ½
    -0.27
    iless
    -0.26
    Enough
    -0.24
     Prosec
    -0.24
    ç¼Ĭ
    -0.24
     Craw
    -0.24
    ä¹ŁåºĶ该
    -0.24
    POSITIVE LOGITS
    åıĸåĨ³
    0.29
     fix
    0.28
    fait
    0.26
     determining
    0.26
     labor
    0.26
    åĻ¨
    0.26
    FIX
    0.26
     hinges
    0.25
     polynomial
    0.25
    preh
    0.25
    Activations Density 0.034%

    No Known Activations