© 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. 64238
    Prev
    Next
    INDEX
    Explanations

    scientific/technical language

    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
    Lifetime
    -0.28
     quotation
    -0.26
     external
    -0.25
     External
    -0.24
     extern
    -0.24
    inity
    -0.24
     Pub
    -0.24
    kiye
    -0.24
    TMP
    -0.24
    _absolute
    -0.24
    POSITIVE LOGITS
     thereof
    0.30
     therein
    0.30
    phans
    0.28
    pain
    0.27
    lbrace
    0.25
    çĹĽ
    0.24
    ller
    0.24
    arily
    0.23
    æĵ¦
    0.23
    æĸĮ
    0.23
    Activations Density 66.024%

    No Known Activations