© 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. 19-TRANSCODER-HP
    7. 9585
    Prev
    Next
    INDEX
    Explanations

    Providing examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģç±»
    -0.28
     lòng
    -0.28
    ä¹Ī
    -0.27
     appropriation
    -0.26
    å¿ĥæĦı
    -0.25
    »¿
    -0.25
    èĸĦ
    -0.25
    æģŃåĸľ
    -0.25
    ä¸Ģçŀ¬éĹ´
    -0.25
     centers
    -0.24
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.54
     example
    0.52
    çļĦä¾ĭåŃIJ
    0.48
     examples
    0.47
     Examples
    0.41
     Example
    0.40
    举ä¾ĭ
    0.40
    examples
    0.39
     exemp
    0.38
    ä¾ĭ
    0.38
    Activations Density 0.318%

    No Known Activations