© 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. 44585
    Prev
    Next
    INDEX
    Explanations

    eruv carrying nullified kintbury

    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
     clich
    -0.09
    ç²ķ
    -0.07
    çĪĨ
    -0.07
    çī¹èѦ
    -0.07
    èľľæľĪ
    -0.07
    andia
    -0.07
    æ·¬
    -0.06
    éħĹ
    -0.06
    åĪł
    -0.06
    ä¸Ĭä¸ĸ纪
    -0.06
    POSITIVE LOGITS
    azon
    0.08
    ä¸įé½IJ
    0.08
    æĻ®éĢļçļĦ
    0.08
    tev
    0.08
    é¡»ç»ı
    0.08
    çŃīåIJĦç§į
    0.08
    çļĦè§Ħå®ļ
    0.08
    è§Ħå®ļçļĦ
    0.08
    nty
    0.07
    æĺİçŁ¥
    0.07
    Activations Density 0.018%

    No Known Activations