© 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. 50757
    Prev
    Next
    INDEX
    Explanations

    GB/month

    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
    erb
    -0.07
    åĽŀæĥ³
    -0.06
    lend
    -0.06
    лана
    -0.06
     pó
    -0.06
     Abram
    -0.06
    gz
    -0.06
    ç§Ģ
    -0.06
    fw
    -0.06
     ex
    -0.06
    POSITIVE LOGITS
    èijĨ
    0.08
    第ä¸Ģ线
    0.08
    ä½Ĩä»įçĦ¶
    0.08
    ä½Ĩä»į
    0.08
    Äħtek
    0.07
    Twig
    0.07
    æĸ°çļĦ
    0.07
    她çİ°åľ¨
    0.07
    still
    0.07
    ÙĦائ
    0.07
    Activations Density 0.017%

    No Known Activations