© 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. 48445
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    ebol
    -0.07
    adm
    -0.07
    BAT
    -0.07
    å¿«çļĦ
    -0.07
    ä¸įå¦Ĥ
    -0.07
     spia
    -0.07
    zyst
    -0.07
     Nunes
    -0.06
    lea
    -0.06
    гаÑĤ
    -0.06
    POSITIVE LOGITS
    olum
    0.08
    ikkert
    0.07
    èĥ½å¤ŁåģļåĪ°
    0.07
    çļĦ人æĺ¯
    0.07
    endo
    0.07
    inggu
    0.07
    noinspection
    0.07
    ä»ĸåį´
    0.07
     Diss
    0.06
    ville
    0.06
    Activations Density 0.001%

    No Known Activations