© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26763
    Prev
    Next
    INDEX
    Explanations

    sprint canoer who

    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
    deen
    -0.07
    ä¹ł
    -0.07
    ENA
    -0.06
     re
    -0.06
    éŸéŨ
    -0.06
    ener
    -0.06
    irsch
    -0.06
     Reit
    -0.06
    èį£
    -0.06
    PM
    -0.06
    POSITIVE LOGITS
    িশ
    0.08
     |[
    0.08
    hazi
    0.07
    hode
    0.07
    å·¥ä½ľå¼Ģå±ķ
    0.07
    è¿ĩåįĬ
    0.07
    ê·¹
    0.07
    .names
    0.07
     **^
    0.07
    ¼
    0.07
    Activations Density 0.001%

    No Known Activations