© 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. 30026
    Prev
    Next
    INDEX
    Explanations

    code identifiers 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
    ed
    -0.08
    s
    -0.07
    asp
    -0.06
    es
    -0.06
    涩
    -0.06
    anker
    -0.06
    schen
    -0.06
     berh
    -0.06
    enu
    -0.06
    aman
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.09
    opsis
    0.08
    ãĢľãĢľ
    0.08
    atif
    0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    0.08
    umos
    0.08
    çij¾
    0.08
    ousel
    0.08
    óf
    0.08
     ä»ĬæĹ¥ãĤĤ
    0.08
    Activations Density 0.003%

    No Known Activations