© 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. 22681
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
    ilter
    -0.07
     appended
    -0.07
    è¡ĮåĪĹ
    -0.06
     shortcode
    -0.06
    å½¼æѤ
    -0.06
    GLOBALS
    -0.06
    inz
    -0.06
    èĹ»
    -0.06
    ÙĨÚ¯
    -0.06
    Moment
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºåıªæľī
    0.08
    åĨħ容çļĦ羣å®ŀæĢ§
    0.07
    stash
    0.07
    undur
    0.07
    æ¨Ĭ
    0.07
    çļĦé±¼
    0.07
    atkan
    0.07
    estad
    0.07
    æĺ¯åIJĹ
    0.07
    pawn
    0.06
    Activations Density 0.002%

    No Known Activations