© 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. 129499
    Prev
    Next
    INDEX
    Explanations

    Data analysis and descriptions

    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
     easily
    -0.26
    zew
    -0.26
    erator
    -0.26
    æĥħåł±ãĤĴ
    -0.25
    ContextHolder
    -0.24
    esch
    -0.24
    éģ¿åħį
    -0.24
     submodule
    -0.23
    个人信æģ¯
    -0.23
     aiding
    -0.23
    POSITIVE LOGITS
    è°ĥæŁ¥æĺ¾ç¤º
    0.28
     equivalent
    0.28
    åIJ¸åħ¥
    0.25
    ’S
    0.25
    æĿ¥çľĭ
    0.24
    æĦıä¹īä¸ĬçļĦ
    0.24
     setContentView
    0.24
     JsonConvert
    0.24
     |_
    0.24
    ibus
    0.24
    Activations Density 69.913%

    No Known Activations