© 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. 129944
    Prev
    Next
    INDEX
    Explanations

    Technical discussions/articles

    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
    achs
    -0.28
    auen
    -0.28
    Optional
    -0.26
    _optional
    -0.26
    ãĥĥãĥĦ
    -0.26
    鸾
    -0.24
    ewan
    -0.24
    nicos
    -0.24
    (horizontal
    -0.23
     Katz
    -0.23
    POSITIVE LOGITS
     already
    0.32
    é¢Ħæ¡Ī
    0.30
    å½ĵçĦ¶
    0.29
    åĩłæŃ¥
    0.29
    already
    0.29
    æĹ©å·²
    0.28
    Already
    0.27
    åIJĮæł·çļĦ
    0.27
    _already
    0.27
    å·²ç»ıæĺ¯
    0.27
    Activations Density 24.562%

    No Known Activations