© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 94942
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     written
    -0.32
    written
    -0.29
     Latin
    -0.29
    书éĿ¢
    -0.27
    Written
    -0.27
    <Unit
    -0.27
    æĭ¼éŁ³
    -0.26
    æĭīä¸ģ
    -0.26
    (Unit
    -0.26
     booklet
    -0.26
    POSITIVE LOGITS
     pul
    0.29
    纫
    0.27
    è´«
    0.26
     Howe
    0.26
    å³°
    0.26
    isky
    0.25
    ä½³
    0.25
    iswa
    0.24
    å·¥
    0.24
    amin
    0.24
    Activations Density 0.101%

    No Known Activations