© 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. 37952
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions$$

    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
    -0.10
    áter
    -0.08
    ————————————————
    -0.08
    åĩºå·®
    -0.07
    lift
    -0.07
    .direction
    -0.07
    {}",
    -0.07
    æ¼ĵ
    -0.07
    _assets
    -0.07
    elsÅij
    -0.07
    POSITIVE LOGITS
    èļ¤
    0.07
     because
    0.06
    åį´åĽłä¸º
    0.06
     alun
    0.06
    is
    0.06
    .Override
    0.06
    æīĵéĢłæĪIJ
    0.06
    ãģªãģĮ
    0.06
    ness
    0.06
    HING
    0.06
    Activations Density 0.001%

    No Known Activations