© 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. 142038
    Prev
    Next
    INDEX
    Explanations

    Computer systems and technical reports

    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
    çµ²
    -0.28
    ä¸įåIJĮç¨ĭ度
    -0.27
    zee
    -0.27
    åĢĴ
    -0.27
    ascimento
    -0.26
    è¿Ļä¹Ī说
    -0.25
    ä¸Ŀ
    -0.25
    é½IJ
    -0.25
    .TextAlignment
    -0.25
    _flutter
    -0.24
    POSITIVE LOGITS
    acle
    0.31
    alten
    0.30
    amed
    0.28
    aler
    0.28
    (ref
    0.27
     proport
    0.27
    /ref
    0.26
    ä½ĵéĩı
    0.26
    çĽ¼
    0.26
    atics
    0.26
    Activations Density 29.097%

    No Known Activations