© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44706
    Prev
    Next
    INDEX
    Explanations

    code structure or programming constructs

    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
    Negative Logits
    èĤ²
    -0.07
    TypeInfo
    -0.07
    leks
    -0.07
    ÑĤÑı
    -0.07
    aktu
    -0.06
     heav
    -0.06
    ÑģÑĤÑĢÑı
    -0.06
    AREST
    -0.06
    sq
    -0.06
    æıIJ
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·ä¸ĢæĿ¥
    0.09
    impa
    0.07
    æѤå¤ĸ
    0.07
    ableObject
    0.07
    borg
    0.07
     यà¥ĩ
    0.07
    erty
    0.06
    (EC
    0.06
    á»įa
    0.06
    urn
    0.06
    Activations Density 0.240%

    No Known Activations