© 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. 107389
    Prev
    Next
    INDEX
    Explanations

    a

    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
    vol
    -0.31
    [now
    -0.28
    ÅĤó
    -0.26
    IGN
    -0.26
    IFn
    -0.25
    UDA
    -0.25
    ren
    -0.25
    ثاÙĨ
    -0.25
    没åķ¥
    -0.25
    ertura
    -0.24
    POSITIVE LOGITS
    ially
    0.30
    ahrung
    0.29
    å¥Ĺ
    0.28
    hea
    0.27
     converse
    0.26
    çĪ·
    0.25
    æĺ¯æĢİæł·
    0.25
     Gros
    0.24
     Toolbox
    0.24
    ãģ¯ãģ©ãģĨ
    0.24
    Activations Density 9.628%

    No Known Activations