© 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. 9574
    Prev
    Next
    INDEX
    Explanations

    Technical media and legal documents

    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
    çļĦæĪIJæľ¬
    -0.29
    panels
    -0.28
    溲
    -0.28
    _COMPILE
    -0.27
    éķ¿å¤§äºĨ
    -0.26
    åĴ¨
    -0.26
    ëĭĿ
    -0.25
    åĸĩ
    -0.25
    (Runtime
    -0.24
    Ãło
    -0.24
    POSITIVE LOGITS
    çĸĿ
    0.29
    uate
    0.27
    avic
    0.26
    窦
    0.25
    ÃĹ↵↵
    0.24
    bred
    0.24
    istic
    0.23
     sple
    0.23
    çĪ±ä¸Ĭ
    0.23
    erspective
    0.23
    Activations Density 0.003%

    No Known Activations