© 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. 44739
    Prev
    Next
    INDEX
    Explanations

    themes, categories, topics, pillars, or sections

    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
    Negative Logits
    åľ¨éĿŀ
    -0.07
     trivial
    -0.07
    åĿIJåľ¨
    -0.07
    æĢ¥
    -0.07
    æĭ¿
    -0.07
    å±ŀ
    -0.07
    odar
    -0.07
    è°ħ
    -0.06
    olation
    -0.06
    åĴ«å°º
    -0.06
    POSITIVE LOGITS
    emet
    0.09
    åıĪä¸Ģ个
    0.08
     systematically
    0.08
    icont
    0.08
    主é¢ĺ
    0.07
    ä¸ĭ设
    0.07
    ovens
    0.07
    indert
    0.07
     xuyên
    0.07
    æĪij身边
    0.07
    Activations Density 0.023%

    No Known Activations