© 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. 20-TRANSCODER-HP
    7. 107172
    Prev
    Next
    INDEX
    Explanations

    Long, specific, technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åīįåIJİ
    -0.38
    æĺ¯åIJ¦
    -0.35
    ä¸İåIJ¦
    -0.33
     whether
    -0.33
     different
    -0.32
     versus
    -0.31
     various
    -0.31
    é«ĺä½İ
    -0.31
     differently
    -0.31
    æľīä¸įåIJĮçļĦ
    -0.31
    POSITIVE LOGITS
    åĪĨéĴŁåIJİ
    0.32
     unless
    0.31
    unless
    0.28
    Except
    0.27
    Unless
    0.26
     except
    0.26
    ãģ®æĸ¹ãģĮ
    0.26
    èĢĮ对äºİ
    0.26
    并ä¸Ķ
    0.26
    Meanwhile
    0.26
    Activations Density 69.732%

    No Known Activations