© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51918
    Prev
    Next
    INDEX
    Explanations

    code ending with `then` or `beginTransaction`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agal
    -0.07
    å¦Ĥä¸ĭåĽ¾
    -0.07
    èĭ±æĸĩåIJįåŃĹ
    -0.07
     tehát
    -0.07
    çļĦåĽ¾çīĩ
    -0.07
    niÄĻ
    -0.06
    áĢ±áĢ¬áĢĦáĢº
    -0.06
     appropriately
    -0.06
    çļĦæŶåĢĻä¸Ģå®ļè¦ģ
    -0.06
    odore
    -0.06
    POSITIVE LOGITS
    æĪIJåĬŁåIJİåį³åı¯
    0.08
    (___
    0.07
     [âĢ¦]
    0.07
    ${
    0.07
    0.07
    <|im_end|>
    0.07
     [...]
    0.06
    \"
    0.06
    .${
    0.06
     \"
    0.06
    Activations Density 0.179%

    No Known Activations