© 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. 22306
    Prev
    Next
    INDEX
    Explanations

    math and code context

    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
    èµĽåIJİ
    -0.07
    å¿ħçľĭ
    -0.07
    imulator
    -0.07
    aszt
    -0.07
    tester
    -0.06
    æĪijæĢķ
    -0.06
     Tester
    -0.06
    icali
    -0.06
     ÑģвидеÑĤ
    -0.06
    -comments
    -0.06
    POSITIVE LOGITS
     straightforward
    0.08
    antro
    0.07
    çļĦ缴æİ¥
    0.07
    bogen
    0.07
    aukee
    0.07
    ifr
    0.07
    Simply
    0.07
     simply
    0.07
    JECTED
    0.07
    å¾Īç®Ģåįķ
    0.06
    Activations Density 0.028%

    No Known Activations