© 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. 41291
    Prev
    Next
    INDEX
    Explanations

    left or nearest

    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
    ÑİÑĢа
    -0.08
    ENU
    -0.08
     Horton
    -0.08
    è´¢åĬ¡æĬ¥åijĬ
    -0.08
    shot
    -0.08
    ÙĪارÙĩ
    -0.07
     εγκ
    -0.07
    ntax
    -0.07
    åĸĥ
    -0.07
    reach
    -0.07
    POSITIVE LOGITS
    åħ±åIJĮ
    0.09
    åħ±åIJĮçļĦ
    0.08
    çļĦåħ±åIJĮ
    0.08
    åħ±çĶ¨
    0.08
     common
    0.08
    åħ±åIJĮè¿ĽæŃ¥
    0.07
     shared
    0.07
    à¸Ĺัà¹īà¸ĩ
    0.06
    اص
    0.06
    åħ±æľī
    0.06
    Activations Density 0.001%

    No Known Activations