© 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. 17882
    Prev
    Next
    INDEX
    Explanations

    applepineapplefruit

    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
    没æľīæŶéĹ´
    -0.07
    è¹ĭ
    -0.07
    ouples
    -0.07
    bland
    -0.07
    angkan
    -0.07
    hash
    -0.07
     Suns
    -0.07
    è¿ħ鼷ä¸ĭè½½
    -0.06
    ä¸įå¦Ļ
    -0.06
    оÑĩ
    -0.06
    POSITIVE LOGITS
    اÛĮØ´
    0.08
    jos
    0.07
    jaht
    0.07
    ULK
    0.07
    _INCLUDED
    0.07
    ÏģαÏĥ
    0.07
    urah
    0.07
    æĶ¶ä¸ĭ
    0.07
    ansom
    0.06
    èİŀ
    0.06
    Activations Density 0.034%

    No Known Activations