© 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. 33-TRANSCODER-HP
    7. 54760
    Prev
    Next
    INDEX
    Explanations

    how

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ematic
    -0.31
    .c
    -0.27
    天
    -0.27
    游
    -0.26
    C
    -0.26
    \Unit
    -0.26
    icient
    -0.26
    (
    -0.26
    .n
    -0.25
    æĹł
    -0.25
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.29
    们éĥ½
    0.28
     afterwards
    0.28
    åİ»çľĭçľĭ
    0.28
    éĩĮéĿ¢æľī
    0.28
     afar
    0.27
    æł¹æľ¬å°±ä¸į
    0.27
    è¿ĩç¨ĭå½ĵä¸Ń
    0.27
    çľĭä½ł
    0.27
     originals
    0.27
    Activations Density 0.082%

    No Known Activations