© 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. 24010
    Prev
    Next
    INDEX
    Explanations

    code snippet with examples

    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
    çĥģ
    -0.08
    Č↵
    -0.07
    ׼׾
    -0.07
     ãģĬçŁ¥ãĤīãģĽ
    -0.07
    çī¹å²Ĺ
    -0.07
    æıIJ示信æģ¯
    -0.07
    æĸ°éĹ»åªĴä½ĵ
    -0.07
     bearer
    -0.07
    -animate
    -0.07
    éĹ´æŃĩ
    -0.07
    POSITIVE LOGITS
     calculations
    0.10
    åħ·ä½ĵåĪĨæŀIJ
    0.08
    çļĦ计ç®Ĺ
    0.08
     mathematical
    0.08
    æķ°åѦ
    0.08
     approximate
    0.08
    计ç®Ĺ
    0.08
     calculation
    0.08
     math
    0.07
    ascal
    0.07
    Activations Density 0.027%

    No Known Activations