© 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. 8003
    Prev
    Next
    INDEX
    Explanations

    vice versa

    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
    è¿ľè¿ľ
    -0.07
    udos
    -0.07
    çĭ¬
    -0.07
    è¿ľä½İäºİ
    -0.07
    éĿŀçī©è´¨
    -0.07
    约æĿŁ
    -0.07
    kul
    -0.07
     доли
    -0.07
    िय
    -0.07
     itself
    -0.06
    POSITIVE LOGITS
     whichever
    0.10
     reversed
    0.10
     confusion
    0.09
    é¢łåĢĴ
    0.09
    æĽ´æĸ¹ä¾¿
    0.09
     convenience
    0.09
     convenient
    0.09
    åıį转
    0.09
    åĢĴ
    0.08
     conventions
    0.08
    Activations Density 0.002%

    No Known Activations