© 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. 10932
    Prev
    Next
    INDEX
    Explanations

    numerical 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
    æ±Ĺ
    -0.07
    uh
    -0.07
    anny
    -0.06
    rese
    -0.06
     ambit
    -0.06
    witz
    -0.06
    uo
    -0.06
    urat
    -0.06
    λλη
    -0.06
     ä»ĬæĹ¥
    -0.06
    POSITIVE LOGITS
     ëģ
    0.07
    венÑĮ
    0.07
     already
    0.07
    wares
    0.07
    adah
    0.07
    jobb
    0.06
     Indexed
    0.06
     Prac
    0.06
    ippet
    0.06
    éĿĻ
    0.06
    Activations Density 0.005%

    No Known Activations