© 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. 129474
    Prev
    Next
    INDEX
    Explanations

    large quantities

    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
     Webster
    -0.27
    HashSet
    -0.26
    .Please
    -0.25
    ement
    -0.25
    esor
    -0.25
     Wang
    -0.25
    æĹ·
    -0.24
    aron
    -0.24
    .SP
    -0.24
     Fahrenheit
    -0.24
    POSITIVE LOGITS
    pch
    0.33
    IFE
    0.28
     dbc
    0.27
    fty
    0.25
     jlong
    0.25
    æľīæŶ
    0.25
    pix
    0.25
    inja
    0.25
    yc
    0.24
    psy
    0.24
    Activations Density 3.192%

    No Known Activations