© 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. 43300
    Prev
    Next
    INDEX
    Explanations

    code referencing client or c++ structures

    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
    ully
    -0.08
    insa
    -0.07
    rog
    -0.07
    没æŶéĹ´
    -0.07
    ][_
    -0.07
    urin
    -0.06
    æ³ķå¾ĭåĴĮ
    -0.06
    aring
    -0.06
    é»Ħæ²Ļ
    -0.06
    aspers
    -0.06
    POSITIVE LOGITS
     WINAPI
    0.09
    mbH
    0.08
    unds
    0.07
    economia
    0.07
     berv
    0.07
    REEN
    0.07
    ::~
    0.06
     GRATIS
    0.06
     licha
    0.06
    arder
    0.06
    Activations Density 0.085%

    No Known Activations