© 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. 35-TRANSCODER-HP
    7. 38830
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    was
    -0.84
     was
    -0.82
     Was
    -0.75
    Was
    -0.74
    _was
    -0.65
     WAS
    -0.63
     wasn
    -0.56
     бÑĭла
    -0.45
     бÑĭл
    -0.44
     était
    -0.42
    POSITIVE LOGITS
    ä»ĸ们ä¼ļ
    0.32
    ä»Ģä¹Īåij¢
    0.30
    ä»ĸ认为
    0.30
    æĪij们ä¼ļ
    0.29
    æīįæľī
    0.28
    æĪij们åºĶ该
    0.28
    è¿ĻéĩĮæľī
    0.28
    ä»ĭç»įä¸Ģä¸ĭ
    0.28
    ä»ĸå·²ç»ı
    0.28
    ãģĦãĤĮãģ°
    0.28
    Activations Density 10.073%

    No Known Activations