© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13544
    Prev
    Next
    INDEX
    Explanations

    percentage of

    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
    åı½
    -0.08
    éĢ£ãĤĮ
    -0.07
    mixed
    -0.07
    ingo
    -0.07
    软硬
    -0.07
    ActionResult
    -0.07
    pio
    -0.07
    ivate
    -0.07
    ä¸Ģç§įæĺ¯
    -0.07
    åħįè´¹é¢Ĩåıĸ
    -0.07
    POSITIVE LOGITS
    è´¡çĮ®
    0.14
    åįłæĢ»
    0.13
     contribution
    0.12
     disproportionately
    0.12
     contributions
    0.12
     Contribution
    0.12
    è²¢çį»
    0.12
    åįłåħ¨åĽ½
    0.11
    éĽĨä¸Ń
    0.11
    çļĦè´¡çĮ®
    0.11
    Activations Density 0.107%

    No Known Activations