© 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. 59997
    Prev
    Next
    INDEX
    Explanations

    elements and parts

    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
    ï¸İ
    -0.07
    èį·å°ĶèĴĻ
    -0.07
    æı½
    -0.07
    ,no
    -0.07
    vince
    -0.06
    ariat
    -0.06
    beren
    -0.06
    ernes
    -0.06
     bè
    -0.06
    volent
    -0.06
    POSITIVE LOGITS
    æŁIJ个
    0.13
    æŁIJç§į
    0.12
    æŁIJ
    0.12
    æŁIJåĢĭ
    0.11
    æŁIJä¸Ģ
    0.11
    åľ¨æŁIJ
    0.10
    æŁIJäºĽ
    0.10
     certain
    0.10
     somehow
    0.09
    æŁIJ人
    0.09
    Activations Density 0.001%

    No Known Activations