© 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. 141381
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    æľĿ
    -0.30
     fr
    -0.28
    dash
    -0.26
    å¾Ģ
    -0.26
     py
    -0.26
     results
    -0.26
     grand
    -0.26
    swith
    -0.26
    ponsor
    -0.26
    hin
    -0.25
    POSITIVE LOGITS
    CTYPE
    0.30
    ¤í
    0.28
    æĻ¡
    0.27
     Initial
    0.27
    èµ·åĪĿ
    0.26
    (dtype
    0.24
    [next
    0.24
     poczÄħtk
    0.24
    Await
    0.24
     Atmos
    0.24
    Activations Density 8.080%

    No Known Activations