© 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. 11896
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    edes
    -0.09
    íĻĺ
    -0.08
    аем
    -0.07
    uster
    -0.07
    es
    -0.07
    ษา
    -0.07
    OrCreate
    -0.07
    бил
    -0.07
    aÄĩ
    -0.07
    iena
    -0.07
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    coli
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    俱ä¹IJéĥ¨
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    á»ĥn
    0.07
    maÃŁen
    0.07
    bidden
    0.07
    lav
    0.07
    Activations Density 0.004%

    No Known Activations