© 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. 41485
    Prev
    Next
    INDEX
    Explanations

    non-English characters or punctuation

    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
    西èĴĻ
    -0.07
     Sim
    -0.07
     Licensed
    -0.06
    延
    -0.06
    çĽ¸å¯¹
    -0.06
    aban
    -0.06
    æŀī
    -0.06
    ULE
    -0.06
    åIJİç½®
    -0.06
    اسب
    -0.06
    POSITIVE LOGITS
    å±±é«ĺ
    0.08
    åĩºäºº
    0.08
    /native
    0.08
    _guess
    0.07
    tta
    0.07
    ennes
    0.07
    æļĹæģĭ
    0.07
    sang
    0.07
    .fs
    0.07
    使èĩªå·±çļĦ
    0.07
    Activations Density 0.001%

    No Known Activations