© 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. 35-TRANSCODER-HP
    7. 40408
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChangeEvent
    -0.33
    -changing
    -0.28
    çļĦæŃ¥ä¼IJ
    -0.26
    gne
    -0.25
    <Entry
    -0.24
     bystand
    -0.24
     Bison
    -0.24
    .Direct
    -0.23
     missed
    -0.23
    åĴ«
    -0.23
    POSITIVE LOGITS
    ç«ĭåĪ»
    0.33
    ä¸¥æł¼
    0.32
    åħ¬å¼Ģ
    0.28
    çľĭä¸įè§ģ
    0.27
    æ²Ļåıij
    0.27
    继ç»Ń
    0.26
    èĮĥåĽ´
    0.26
    åĸľæ¬¢
    0.25
    rang
    0.25
    为空
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.