© 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. 63876
    Prev
    Next
    INDEX
    Explanations

    word origins and definitions

    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
    è¿Ļ个åIJįåŃĹ
    -0.26
    иÑĢование
    -0.25
    èĢIJ磨
    -0.25
    è¡Įäºĭ
    -0.25
    gin
    -0.25
    æĨĭ
    -0.24
    硬
    -0.24
    [word
    -0.24
    eo
    -0.24
    åıįå°Ħ
    -0.23
    POSITIVE LOGITS
    éĿ¢
    0.26
    CompanyId
    0.26
    comm
    0.25
    çļĦæĪIJåĬŁ
    0.24
    idental
    0.24
    aseline
    0.24
    CALLTYPE
    0.24
    bsolute
    0.24
    uintptr
    0.24
    Medium
    0.24
    Activations Density 3.349%

    No Known Activations