© 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. 16404
    Prev
    Next
    INDEX
    Explanations

    browser vendor prefixes

    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
    åIJĮæĹ¥
    -0.07
    é»
    -0.07
    æ§IJ
    -0.07
    èĻ±
    -0.06
     Pfeffer
    -0.06
    ihil
    -0.06
    ä¹Ķæľ¨
    -0.06
    大æĸ¹
    -0.06
    级åĪ«çļĦ
    -0.06
    ä¼ģä¸ļæīĢå¾Ĺç¨İ
    -0.06
    POSITIVE LOGITS
    stown
    0.08
    åı·è§Ĵ
    0.08
    ardino
    0.08
     fabr
    0.07
    好æĸĩ
    0.07
     eql
    0.07
    _DER
    0.07
    ä¸į离
    0.07
    ä»Ģ
    0.07
    è¦ļ
    0.07
    Activations Density 0.001%

    No Known Activations