© 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. 34885
    Prev
    Next
    INDEX
    Explanations

    introduces definition or list

    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
    ÅŁk
    -0.07
    oop
    -0.07
    ielle
    -0.07
    öse
    -0.07
    িয়à§ĩ
    -0.07
    诸å¦Ĥ
    -0.07
    zil
    -0.07
     vice
    -0.07
    æŀ«
    -0.06
    éĥ½å¥½
    -0.06
    POSITIVE LOGITS
    olf
    0.07
    erge
    0.07
    äºĭæĪIJ
    0.06
    ä¸Ń磩
    0.06
    inho
    0.06
    oftware
    0.06
     âĸ·
    0.06
    inium
    0.06
    achsen
    0.06
    ptest
    0.06
    Activations Density 0.037%

    No Known Activations