© 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. 45618
    Prev
    Next
    INDEX
    Explanations

    numbers, code, and technical terms

    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
     SEEK
    -0.07
    зиÑĢа
    -0.07
    ëĿ¼ëıĦ
    -0.07
    (prefix
    -0.07
    ssel
    -0.06
    路交åıīåı£
    -0.06
    Æ°
    -0.06
     weshalb
    -0.06
    .seek
    -0.06
    ost
    -0.06
    POSITIVE LOGITS
    kut
    0.07
    ØŃÙħاÙħ
    0.07
    æĸ°åĬłåĿ¡
    0.07
    æ²IJ
    0.07
     nau
    0.07
    转载èĩª
    0.07
    اÙĦÙĥترÙĪ
    0.07
    oksi
    0.07
    Fcn
    0.07
    æĻ®æ£®
    0.07
    Activations Density 0.001%

    No Known Activations