© 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. 22674
    Prev
    Next
    INDEX
    Explanations

    my code examples

    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
    æ¶İ
    -0.07
    à¸Ħ
    -0.07
    quire
    -0.07
    èĬĿ
    -0.06
     Buf
    -0.06
    øv
    -0.06
    éĤ£æŶ
    -0.06
     olim
    -0.06
    éĤ£æŶåĢĻ
    -0.06
    åIJĦç§į
    -0.06
    POSITIVE LOGITS
    使çĶ¨çļĦæĺ¯
    0.08
    注åĨĮä¼ļåijĺ
    0.08
    çĶ¨çļĦæĺ¯
    0.08
    ugg
    0.08
    å±ħçĦ¶æĺ¯
    0.07
    AccessType
    0.07
    æīĵåĩºäºĨ
    0.07
    使çĶ¨äºĨ
    0.07
    رÙĪÛĮ
    0.07
    åIJį为
    0.07
    Activations Density 0.002%

    No Known Activations