© 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. 130334
    Prev
    Next
    INDEX
    Explanations

    Math and random characters

    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
     defs
    -0.26
    åįľ
    -0.26
    :def
    -0.25
    TURE
    -0.25
    ëĭĪëĭ¤
    -0.25
    ajs
    -0.25
    åŃIJå¼Ł
    -0.24
    è°Ģ
    -0.24
     légère
    -0.24
     living
    -0.24
    POSITIVE LOGITS
     figure
    0.28
    }&
    0.27
     troub
    0.27
    weeney
    0.27
    mann
    0.27
    neau
    0.27
    nton
    0.26
    steller
    0.26
    sworth
    0.25
    esso
    0.25
    Activations Density 0.291%

    No Known Activations