© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29779
    Prev
    Next
    INDEX
    Explanations

    probability distributions and mathematical notations

    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
    icont
    -0.09
    bbe
    -0.07
    åīį两
    -0.07
    hle
    -0.07
    oare
    -0.07
    æĪijè¡Į
    -0.07
    tw
    -0.07
    osci
    -0.07
    igs
    -0.07
     rec
    -0.07
    POSITIVE LOGITS
    leich
    0.08
    ä»ĸèĩªå·±
    0.08
    áp
    0.07
    anken
    0.07
    inaug
    0.07
    ä»ĸèĩªå·±çļĦ
    0.06
    ãĥĥãĤ»
    0.06
     FileMode
    0.06
    äºİ
    0.06
    åħ¼
    0.06
    Activations Density 0.003%

    No Known Activations