© 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. 43248
    Prev
    Next
    INDEX
    Explanations

    scientific notation with exponents

    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
     beg
    -0.08
    abil
    -0.08
    ahan
    -0.07
    amera
    -0.07
    chwitz
    -0.07
    éĩį大çļĦ
    -0.07
    ardon
    -0.07
    nem
    -0.07
    urator
    -0.06
    ser
    -0.06
    POSITIVE LOGITS
    AKER
    0.07
    aker
    0.07
    »
    0.07
    æ¼ĶçļĦ
    0.07
    cmds
    0.07
    ought
    0.06
    erce
    0.06
    erde
    0.06
    çݺ
    0.06
    lsen
    0.06
    Activations Density 0.021%

    No Known Activations