© 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. 43661
    Prev
    Next
    INDEX
    Explanations

    mild conditions

    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
    æķ°éĩı为
    -0.08
    metry
    -0.07
    é»Ħæ²Ļ
    -0.07
    .untracked
    -0.07
     Fortune
    -0.07
    éļ¾æ±Ĥ
    -0.07
     perspective
    -0.07
    หาà¸Ķ
    -0.07
    изо
    -0.07
     quantity
    -0.06
    POSITIVE LOGITS
    è¿ľä½İäºİ
    0.11
     gentle
    0.11
    温åĴĮ
    0.10
     temperatures
    0.09
    ä½İ温
    0.09
    Low
    0.09
    çļĦ温度
    0.09
    太ä½İ
    0.09
    ä½İèĩ³
    0.08
    è¶Ĭä½İ
    0.08
    Activations Density 0.044%

    No Known Activations