© 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. 2946
    Prev
    Next
    INDEX
    Explanations

    Year Anniversary

    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
    äºĨ解èĩªå·±
    -0.07
    erge
    -0.07
    perk
    -0.07
    ogne
    -0.07
    å°±åı¯ä»¥äºĨ
    -0.07
    ersen
    -0.07
    äºĨ解èĩªå·±çļĦ
    -0.07
    gez
    -0.07
    lessly
    -0.07
    å³°çļĦ
    -0.07
    POSITIVE LOGITS
    kais
    0.07
    sstr
    0.07
    就好æ¯Ķ
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    abel
    0.06
    alog
    0.06
    akest
    0.06
    ouses
    0.06
     cah
    0.06
    oot
    0.06
    Activations Density 0.002%

    No Known Activations