© 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. 55957
    Prev
    Next
    INDEX
    Explanations

    basics and fundamentals

    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
    tributes
    -0.07
    åĬłçıŃåĬłçĤ¹
    -0.07
    åĨįæİ¥åĨįåİī
    -0.07
    ancis
    -0.06
    éĿĴå·ŀ
    -0.06
    ë§IJ
    -0.06
     Whip
    -0.06
    éŀĺ
    -0.06
    kki
    -0.06
    ä¸ĢæŶ
    -0.06
    POSITIVE LOGITS
     basics
    0.13
    çIJĨ论ä¸İ
    0.11
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.10
    çIJĨè®ºçŁ¥è¯Ĩ
    0.10
     fundamentals
    0.10
    basic
    0.10
    åŁºæľ¬çŁ¥è¯Ĩ
    0.09
     basic
    0.09
     Basics
    0.09
    æĸ¹éĿ¢çļĦçŁ¥è¯Ĩ
    0.09
    Activations Density 0.183%

    No Known Activations