© 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. 56737
    Prev
    Next
    INDEX
    Explanations

    set of possibilities

    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
    odin
    -0.07
    rud
    -0.07
    ä»ĭ
    -0.07
    ç»´äºļ
    -0.07
     Gratuit
    -0.07
    cce
    -0.07
    æĬĵ
    -0.07
    交æµģä¸İ
    -0.06
    phan
    -0.06
    mand
    -0.06
    POSITIVE LOGITS
    åı¯è¡ĮçļĦ
    0.10
     possibilities
    0.10
     plausible
    0.10
     possible
    0.10
     Possible
    0.10
    åı¯èĥ½çļĦ
    0.09
    Possible
    0.09
     viable
    0.09
    ossible
    0.09
     Narrow
    0.09
    Activations Density 0.021%

    No Known Activations