© 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. 1971
    Prev
    Next
    INDEX
    Explanations

    men and women

    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
    ạch
    -0.08
    ][]
    -0.08
    åĩłåıª
    -0.08
    .Done
    -0.07
    .Singleton
    -0.07
     Äijếm
    -0.07
    ekan
    -0.07
    .Batch
    -0.07
    åı¯æľīæķĪ
    -0.07
    åĽ¢åijĺ
    -0.07
    POSITIVE LOGITS
    温度为
    0.13
    æµĵ度为
    0.11
    ä½İèĩ³
    0.11
    设å®ļçļĦ
    0.11
    æłĩåĩĨ为
    0.09
    贷款åĪ©çİĩ
    0.09
    设å®ļ
    0.09
    ä½İçļĦ
    0.09
    åİĭä½İ
    0.09
     temperatures
    0.09
    Activations Density 1.508%

    No Known Activations