© 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. 10576
    Prev
    Next
    INDEX
    Explanations

    programming code and mathematical expressions

    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
    ç¡®æľī
    -0.07
    æľĢæĸ°èµĦ讯
    -0.07
    /dr
    -0.07
    ÃīG
    -0.07
    æģ¶
    -0.07
    å¾¹
    -0.07
    align
    -0.07
    æĤª
    -0.06
    æĭĶæ²³
    -0.06
    æłĸæģ¯
    -0.06
    POSITIVE LOGITS
    人æĹł
    0.08
    åł°
    0.08
    idy
    0.07
     derp
    0.07
    вани
    0.07
    ptime
    0.07
    ÙİÙĦÙİ
    0.07
    ovel
    0.07
     disap
    0.07
    å¿ĺæĢĢ
    0.07
    Activations Density 0.006%

    No Known Activations