© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8305
    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
    è¿Ļå¥Ĺ
    -0.35
    åįı
    -0.26
    itary
    -0.26
     unique
    -0.26
    uniq
    -0.24
    iram
    -0.24
    è¯¥æł¡
    -0.24
    设计æĸ¹æ¡Ī
    -0.23
    ä¼ļè§ģ
    -0.23
    å¥¹åľ¨
    -0.23
    POSITIVE LOGITS
    表éĿ¢
    0.30
    pas
    0.27
    表éĿ¢ä¸Ĭ
    0.26
    åĽ°
    0.25
    .roll
    0.25
    -outline
    0.24
     rolls
    0.24
    ÙĤاد
    0.24
    |--
    0.24
     rollers
    0.23
    Activations Density 0.056%

    No Known Activations

    This feature has no known activations.