© 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. 63217
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts and questions

    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
    intel
    -0.26
     nø
    -0.24
    èĭ±çī¹
    -0.24
    客æĪ·æıIJä¾Ľ
    -0.23
     Pied
    -0.23
    ropical
    -0.23
    åľ°çIJĥä¸Ĭ
    -0.23
    å¼¼
    -0.23
    ï½ŀ↵↵
    -0.23
    ictionary
    -0.22
    POSITIVE LOGITS
    å®ī
    0.28
    æĭĸ
    0.25
     drag
    0.25
    leys
    0.24
    æĿ¥è®²
    0.24
     Drag
    0.23
    elpers
    0.23
    鸾
    0.23
    lik
    0.23
    ebra
    0.23
    Activations Density 47.964%

    No Known Activations