© 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. 707
    Prev
    Next
    INDEX
    Explanations

    symbols, game inputs, or sports match results

    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
    _keep
    -0.07
    1
    -0.07
    acer
    -0.06
    PF
    -0.06
    çѱ
    -0.06
    ar
    -0.06
    èĨ³
    -0.06
     since
    -0.06
    orum
    -0.06
    KP
    -0.06
    POSITIVE LOGITS
    )':
    0.09
    ëĮĢë¡ľ
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.08
    enthe
    0.08
    é¼İé¼İ
    0.08
    åĬłå·¥è®¾å¤ĩ
    0.08
    liz
    0.08
    OrNull
    0.08
    hiba
    0.08
    åı
    0.08
    Activations Density 0.001%

    No Known Activations