© 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. 9358
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    blast
    -0.28
    å·²å®ĮæĪIJ
    -0.26
    afari
    -0.26
    ogne
    -0.25
    طة
    -0.25
    oplast
    -0.24
    _REUSE
    -0.24
    icity
    -0.24
    anco
    -0.23
    icide
    -0.23
    POSITIVE LOGITS
    伸æīĭ
    0.29
    ä»İ严
    0.27
    éļĪ
    0.26
    tickets
    0.26
    åĨį说
    0.25
    ä¸įåIJĥ
    0.25
    еÑĩа
    0.24
     absolutely
    0.24
    ç»Ŀ
    0.24
    榻
    0.23
    Activations Density 0.122%

    No Known Activations

    This feature has no known activations.