© 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. 37430
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    å¨ĩ
    -0.08
    pers
    -0.07
    éĵ¶å±±
    -0.07
     ID
    -0.07
    assar
    -0.07
    ouns
    -0.06
    榴
    -0.06
    _md
    -0.06
    rames
    -0.06
    å¯ĨåĪĩéħįåIJĪ
    -0.06
    POSITIVE LOGITS
    opsis
    0.07
    osed
    0.07
    åŃ¦ä»¥èĩ´
    0.07
    опо
    0.07
    osing
    0.07
    (strict
    0.06
    å´©åĿı
    0.06
    olis
    0.06
    anic
    0.06
    ç§Ģ
    0.06
    Activations Density 0.036%

    No Known Activations