© 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. 64184
    Prev
    Next
    INDEX
    Explanations

    mathematics and numbers

    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
    pollo
    -0.33
     inicio
    -0.29
    .shtml
    -0.28
    waters
    -0.28
     onStart
    -0.28
    èµ·çĤ¹
    -0.28
    åĨįéĢł
    -0.27
     warranties
    -0.26
     yyn
    -0.26
    æ¦Ĥ
    -0.26
    POSITIVE LOGITS
     gle
    0.30
    gle
    0.29
     tend
    0.28
     just
    0.28
    just
    0.27
    iams
    0.27
     unders
    0.26
     ma
    0.26
    -how
    0.25
    rosis
    0.25
    Activations Density 6.131%

    No Known Activations