© 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. 129580
    Prev
    Next
    INDEX
    Explanations

    technology and quotes

    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
    etti
    -0.27
    wick
    -0.27
    xico
    -0.25
    ä½ľæģ¯
    -0.24
    ARS
    -0.24
    ndon
    -0.24
    ç¯ĩç«ł
    -0.24
    åıĺéĩı
    -0.24
    ToProps
    -0.24
    Ke
    -0.24
    POSITIVE LOGITS
     excitement
    0.26
     Ideas
    0.25
     colleague
    0.24
    çĥŃæĥħ
    0.24
    .Core
    0.23
     suggestions
    0.23
     Her
    0.23
     Scientists
    0.23
    abler
    0.23
    åħ¬åijĬ称
    0.23
    Activations Density 4.886%

    No Known Activations