© 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. 21347
    Prev
    Next
    INDEX
    Explanations

    interface settings and commands

    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
    ivery
    -0.08
    epend
    -0.07
    ç²Ľ
    -0.07
    alidade
    -0.07
    czo
    -0.07
    _modules
    -0.07
    æľĪçĶŁ
    -0.07
    为ä¿ĥè¿Ľ
    -0.07
    ::$
    -0.07
    antal
    -0.07
    POSITIVE LOGITS
    æīĵå¼Ģ
    0.08
    legacy
    0.08
     opened
    0.08
     оÑĤкÑĢ
    0.08
     оÑĤкÑĢÑĭваеÑĤÑģÑı
    0.07
     opens
    0.07
    Fd
    0.07
    éĢĨæµģ
    0.07
     openings
    0.07
    ÙģتØŃ
    0.07
    Activations Density 0.094%

    No Known Activations