© 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. 46193
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    å±±éķĩ
    -0.08
    efeld
    -0.08
    -eslint
    -0.07
    _mE
    -0.07
    æīĵä¸ĭåĿļå®ŀçļĦåŁºç¡Ģ
    -0.07
    -prefix
    -0.07
    idak
    -0.07
    è¡Įäºij
    -0.07
    çĶŁåľ¨
    -0.07
    ä¸Ĭ说
    -0.07
    POSITIVE LOGITS
    æł½
    0.07
    åħ·
    0.07
    аÑĤаÑĢ
    0.07
    ç²¾
    0.07
    æĪĸå°ij
    0.06
     بس
    0.06
     melee
    0.06
    atering
    0.06
    åįĵ
    0.06
    quito
    0.06
    Activations Density 0.008%

    No Known Activations