© 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. 822
    Prev
    Next
    INDEX
    Explanations

    dependence on factors

    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
    ä¸įè¿Ľè¡Į
    -0.08
    éĿ¢å¯¹
    -0.07
    _PENDING
    -0.07
    ëŁŃ
    -0.07
    inear
    -0.07
    ë¶ķ
    -0.07
    对å¾ħ
    -0.07
    .Enum
    -0.07
    天èµIJ
    -0.07
    ç²¾ç¥ŀä¸ĬçļĦ
    -0.07
    POSITIVE LOGITS
    好åIJİ
    0.07
    UCA
    0.07
    extr
    0.07
     aspect
    0.06
    λÏĮ
    0.06
    arity
    0.06
     EXTR
    0.06
    Exp
    0.06
     particular
    0.06
    atility
    0.06
    Activations Density 0.080%

    No Known Activations