© 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. 26130
    Prev
    Next
    INDEX
    Explanations

    grid points or walls

    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
    .*)
    -0.08
    åľ¨åIJij
    -0.07
    --[
    -0.07
    ukum
    -0.07
    laÅŁtır
    -0.07
    ONY
    -0.07
    ghi
    -0.07
    éģĩä¸Ĭ
    -0.07
    baru
    -0.07
    ä¸İåºĶçĶ¨
    -0.07
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.07
    åĴĮèĩªå·±
    0.07
    è¿ĩ好
    0.07
    è¦ģæ±Ĥåħ¶
    0.07
    åĴĮæľªæĿ¥
    0.07
     anymore
    0.07
    à¸Ľà¸£à¸°
    0.07
    Å¡ti
    0.07
    ä¸ŃçļĦæīĢæľī
    0.07
    ارس
    0.07
    Activations Density 0.014%

    No Known Activations