© 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. 13368
    Prev
    Next
    INDEX
    Explanations

    update or updates

    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
    å¹´å§ĭ
    -0.07
    å¦Ĥæŀľä½łæĺ¯
    -0.07
    éĹ®åĮ»çĶŁ
    -0.07
    åģľæŃ¢äºĨ
    -0.07
    æľĢåIJİæĺ¯
    -0.07
     mute
    -0.07
    æ¯ıå¹´çļĦ
    -0.06
    {/
    -0.06
    æ³Ĭ
    -0.06
    SEARCH
    -0.06
    POSITIVE LOGITS
    æĽ´æĸ°æŶéĹ´
    0.09
     обнов
    0.08
    ä¼ĺåĮĸçļĦ
    0.08
     optimizations
    0.08
    update
    0.08
    -update
    0.08
     updating
    0.08
    .update
    0.07
    èļģ
    0.07
    _updates
    0.07
    Activations Density 0.003%

    No Known Activations