© 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. 51942
    Prev
    Next
    INDEX
    Explanations

    falls under category or belonging

    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
    czyk
    -0.08
    ledo
    -0.08
    chten
    -0.07
    лио
    -0.06
     Ø®ÙĦاÙĦÙĩا
    -0.06
    åĮĹæĸ¹çļĦ
    -0.06
    ngle
    -0.06
    resh
    -0.06
    æĹłå¤Ħä¸įåľ¨
    -0.06
    deo
    -0.06
    POSITIVE LOGITS
    èĮĥçķ´
    0.10
     realm
    0.09
     realms
    0.09
     category
    0.08
    å±ŀäºİ
    0.08
    é«ĺåıij
    0.08
     squarely
    0.08
    æŃ£è½¨
    0.08
    ç±»åĪ«
    0.08
    ä¹ĭåĪĹ
    0.08
    Activations Density 0.538%

    No Known Activations