© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57786
    Prev
    Next
    INDEX
    Explanations

    converting string to uppercase or lower

    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
    弧
    -0.07
     arc
    -0.07
    own
    -0.07
    æ¼ĶæĪı
    -0.07
    lad
    -0.07
    elles
    -0.07
    çº¢æŁ¿
    -0.06
    oker
    -0.06
     Arc
    -0.06
    ese
    -0.06
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.08
    example
    0.08
    示ä¾ĭ
    0.08
     example
    0.07
     blah
    0.07
    çļĦä¾ĭåŃIJ
    0.07
    reeting
    0.07
     Bla
    0.07
    _demo
    0.07
     bla
    0.07
    Activations Density 1.191%

    No Known Activations