© 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. 25-TRANSCODER-HP
    7. 108320
    Prev
    Next
    INDEX
    Explanations

    steel production, industrial processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æįIJ
    -0.30
    ymous
    -0.30
    rade
    -0.27
    кладÑĭва
    -0.27
    peated
    -0.26
    ioned
    -0.26
    æĮ½åĽŀ
    -0.26
    -digit
    -0.25
    ERA
    -0.25
    edBy
    -0.25
    POSITIVE LOGITS
    _OPTS
    0.31
    hood
    0.29
     proclamation
    0.28
    arts
    0.28
    HING
    0.26
    commercial
    0.26
    ä¸ŃåĽ½å¤§éĻĨ
    0.25
    课é¢ĺ
    0.25
    ç±»åŀĭ
    0.25
    ç§įç±»
    0.25
    Activations Density 0.165%

    No Known Activations