© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 65069
    Prev
    Next
    INDEX
    Explanations

    font face

    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
    Not in Any Lists

    No Comments

    Negative Logits
    à§ĭরà§į
    -0.08
    ধান
    -0.08
    Callable
    -0.08
    ilor
    -0.07
    å§Ĩæĸ¯
    -0.07
    好èĩªå·±çļĦ
    -0.07
    oord
    -0.07
    转æŃ£
    -0.07
    å»ī
    -0.07
    æĺ¯åĪ©çĶ¨
    -0.07
    POSITIVE LOGITS
    彬
    0.08
    Ùij
    0.07
    acr
    0.07
     Q
    0.06
     Pue
    0.06
    Å¡n
    0.06
     subtract
    0.06
    ery
    0.06
    enses
    0.06
    _editor
    0.06
    Activations Density 0.002%

    No Known Activations