© 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. 107731
    Prev
    Next
    INDEX
    Explanations

    the

    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
    adas
    -0.26
    带åĪ°
    -0.25
    .createComponent
    -0.25
     sometime
    -0.25
     adj
    -0.25
    createQuery
    -0.24
     Voc
    -0.24
    afka
    -0.24
    oda
    -0.24
     culture
    -0.24
    POSITIVE LOGITS
    æģ¶åĬ£
    0.27
    xious
    0.27
    ownload
    0.25
    æĿĥçĽĬ
    0.25
    ä¸Ŀ
    0.25
    æł¼å°Ķ
    0.24
    å¦Ĥæŀľä¸įæĺ¯
    0.24
    ìŀħ
    0.24
    æĪij们就
    0.24
    éĵħ
    0.24
    Activations Density 10.916%

    No Known Activations