© 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. 48978
    Prev
    Next
    INDEX
    Explanations

    column and row structure

    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
    åħ¨æĸĩ
    -0.08
     netr
    -0.08
    åģľçķĻåľ¨
    -0.08
    åģľæŃ¢
    -0.07
    åģľçĶ¨
    -0.07
    寨
    -0.07
    置身
    -0.07
     tph
    -0.07
    _interrupt
    -0.07
    è·Łè´´
    -0.07
    POSITIVE LOGITS
    ä¸Ģ并
    0.10
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    deal
    0.08
    ä¸Ģèµ·æĿ¥
    0.08
    åĮħæĭ¬äºĨ
    0.07
    ä¸Ģèµ·åľ¨
    0.07
    ä¸įèĥ½å®Įåħ¨
    0.07
    Extra
    0.07
    ä¸Ģèµ·
    0.07
    ä¸Ģèµ·åIJĥ
    0.07
    Activations Density 0.064%

    No Known Activations