© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25190
    Prev
    Next
    INDEX
    Explanations

    talking about or meaning

    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
     i
    -0.07
    åijĬ
    -0.06
    æĿIJæĸĻåĴĮ
    -0.06
     I
    -0.06
    çĹ´
    -0.06
    -0.06
    _parsed
    -0.06
    fal
    -0.06
    xyz
    -0.06
     bath
    -0.06
    POSITIVE LOGITS
    æ³ĽæĮĩ
    0.10
    æĮĩçļĦ
    0.10
    éĤ£ç§į
    0.10
     daqu
    0.09
    æĮĩ
    0.09
    ehn
    0.09
    å¨ģ
    0.09
    æĮĩçļĦæĺ¯
    0.09
    éĤ£ç¨®
    0.09
    ä¹ŁåĮħæĭ¬
    0.09
    Activations Density 0.039%

    No Known Activations