© 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. 9150
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    avor
    -0.07
     Realm
    -0.07
    ä¸ŃåĽ½åľ¨
    -0.07
    IfExists
    -0.07
    amel
    -0.07
    itals
    -0.07
     mengap
    -0.07
    iss
    -0.07
    (QObject
    -0.07
    ervo
    -0.07
    POSITIVE LOGITS
     Reinh
    0.08
    /sm
    0.07
    èķ¾
    0.07
    æĢ§æĪĸ
    0.07
     itself
    0.07
     oneself
    0.06
    agam
    0.06
    æī¿æĭħä¸ĢåĪĩ
    0.06
    ensual
    0.06
    æijĩäºĨæijĩ头
    0.06
    Activations Density 0.021%

    No Known Activations