© 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. 20430
    Prev
    Next
    INDEX
    Explanations

    code comment markers

    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
    åı¸
    -0.08
    人家
    -0.07
    (
    -0.06
    å¸ĥæĸ¯
    -0.06
     perl
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    äººä¹Ł
    -0.06
     Gregg
    -0.06
    obo
    -0.06
     sensible
    -0.06
    POSITIVE LOGITS
    çĶ¨èĩªå·±çļĦ
    0.09
    hut
    0.08
    æĬĵåĪ°
    0.08
     ká»ī
    0.08
    åŁºæľ¬ä¿¡æģ¯
    0.08
    anti
    0.08
    æŀļ
    0.08
    æĢĢæı£
    0.08
    ydd
    0.07
    schuss
    0.07
    Activations Density 0.011%

    No Known Activations