© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21786
    Prev
    Next
    INDEX
    Explanations

    multiplying and dividing

    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
    <|box_end|>
    -0.07
    äºİå¿ĥ
    -0.07
    eded
    -0.07
    ston
    -0.07
    å¼Ģå¹ķå¼ı
    -0.07
    并å¸ĮæľĽ
    -0.07
    меÑĢа
    -0.06
    å¦Ļ
    -0.06
    æĽ´å¤ļ精彩
    -0.06
    _MAXIMUM
    -0.06
    POSITIVE LOGITS
    à¹īาย
    0.08
    æ¸ħæ´Ĺå¹²åĩĢ
    0.07
    yata
    0.07
     numerator
    0.06
     denominator
    0.06
     latter
    0.06
    _layout
    0.06
    åIJijåħ¶
    0.06
    orf
    0.06
    uca
    0.06
    Activations Density 0.001%

    No Known Activations