© 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. 34048
    Prev
    Next
    INDEX
    Explanations

    $ math \mathrm{Mat}_n(\mathbb{Z})$ representing continuations products squares

    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
    oly
    -0.07
    åĬªåĬĽåİ»
    -0.07
    ãģĿãģ®ãģ¾ãģ¾
    -0.06
    æľīä½į
    -0.06
     prefer
    -0.06
    æĥ³åĩº
    -0.06
     Outstanding
    -0.06
     repe
    -0.06
    aler
    -0.06
    大åĪĢ
    -0.06
    POSITIVE LOGITS
    æ¸
    0.09
    udson
    0.08
    åŁºå±Ĥåħļ建
    0.07
    adÃŃ
    0.07
    /autoload
    0.07
    ehm
    0.07
    rij
    0.07
    órd
    0.07
    uille
    0.07
    CEE
    0.07
    Activations Density 0.021%

    No Known Activations