© 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. 3512
    Prev
    Next
    INDEX
    Explanations

    numbers and amounts

    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
    -mounted
    -0.08
    æĴ
    -0.06
     :\
    -0.06
    声
    -0.06
    人æ°ijå¸ģæ±ĩçİĩ
    -0.06
    udson
    -0.06
    ãģ«ãģĬãģĦãģ¦
    -0.06
    æĹłè¯Ń
    -0.06
     Arte
    -0.06
    :convert
    -0.06
    POSITIVE LOGITS
    ietf
    0.08
    åŃĺåĤ¨åľ¨
    0.08
    çĦī
    0.08
    çļĦ空éĹ´
    0.07
    tian
    0.07
    patial
    0.07
     xong
    0.07
    ãĤīãģĽ
    0.07
     /^(
    0.07
    æĶ¾åľ¨äºĨ
    0.07
    Activations Density 0.015%

    No Known Activations