© 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. 1995
    Prev
    Next
    INDEX
    Explanations

    references for scientific papers

    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
    ogen
    -0.07
    beau
    -0.07
    æ¦ķ
    -0.06
    unker
    -0.06
    ä¸Ĭ游
    -0.06
    rox
    -0.06
    æŃ¢
    -0.06
    èĩªå¦Ĥ
    -0.06
    ä¼´ä¾£
    -0.06
    åŁºæľ¬åĬŁ
    -0.06
    POSITIVE LOGITS
    åĦ¿çļĦ
    0.08
    á»ı
    0.08
    ç»İ
    0.07
    ATES
    0.07
     erz
    0.07
     trup
    0.07
    .ibm
    0.07
     kori
    0.07
     Vet
    0.07
    æĦıæĥ³
    0.07
    Activations Density 0.029%

    No Known Activations