© 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. 108001
    Prev
    Next
    INDEX
    Explanations

    Code/Technical writing

    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
    olg
    -0.26
    .begin
    -0.25
    =add
    -0.25
    çĪĨ
    -0.24
    åŁ·
    -0.24
    nz
    -0.24
     blas
    -0.24
     зак
    -0.24
     omap
    -0.24
    -op
    -0.24
    POSITIVE LOGITS
    ply
    0.28
    ularity
    0.27
    æĥħ人
    0.25
    ardy
    0.25
    第äºĮ大
    0.25
    pix
    0.25
    hes
    0.25
    licht
    0.25
    uzu
    0.24
    uttle
    0.24
    Activations Density 85.963%

    No Known Activations