© 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. 32585
    Prev
    Next
    INDEX
    Explanations

    large quantities or degree

    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
    亿人
    -0.08
    alian
    -0.08
    į
    -0.08
    ä¸ĩå¹´
    -0.07
     leggermente
    -0.07
    nob
    -0.07
    /stretch
    -0.07
     deteri
    -0.07
    apikey
    -0.07
    åĢįå¢ŀ
    -0.07
    POSITIVE LOGITS
    ç¨ĭ度
    0.10
    以èĩ³äºİ
    0.10
    ç¨ĭ度çļĦ
    0.09
    çļĦç¨ĭ度
    0.09
    ç¨ĭ度ä¸Ĭ
    0.09
    çĶļèĩ³
    0.09
    çĶļèĩ³åı¯ä»¥
    0.09
    以èĩ´
    0.09
     enough
    0.08
     transforms
    0.08
    Activations Density 0.164%

    No Known Activations