© 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. 58941
    Prev
    Next
    INDEX
    Explanations

    `(` or `_` followed by `r`, `flag`, `hash`, `resolve`, `action`, `client`, `item`

    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
     Ñģпа
    -0.08
    ahari
    -0.07
    atal
    -0.07
    åŁł
    -0.07
    atric
    -0.07
     Sede
    -0.07
    ATAL
    -0.07
    ç»´å¥ĩ
    -0.06
    orraine
    -0.06
    ä¸Ńå±±
    -0.06
    POSITIVE LOGITS
     _)
    0.09
     _:
    0.09
    (_,
    0.08
    (_)
    0.08
     (_,
    0.08
    _Rem
    0.08
    _)
    0.07
    еÑĩÑĮ
    0.07
    ieber
    0.07
    contra
    0.07
    Activations Density 0.065%

    No Known Activations