© 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. 24248
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    acÃŃ
    -0.07
    åĭĿ
    -0.07
    顺å¿ĥ
    -0.07
    à¸Ŀà¹īา
    -0.07
     Hert
    -0.07
    unk
    -0.07
    ittel
    -0.07
    ÃįC
    -0.06
    åĩ°
    -0.06
    åħ¨éĥ¨
    -0.06
    POSITIVE LOGITS
    åįĪ
    0.07
     juist
    0.07
    oss
    0.07
    unner
    0.07
    ossed
    0.07
    ndrome
    0.07
    ilent
    0.07
    AMO
    0.07
    æ··åIJĪåŀĭ
    0.07
    æīijéĿ¢èĢĮæĿ¥
    0.07
    Activations Density 0.003%

    No Known Activations