© 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. 61582
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in code or math

    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°ıå®Ŀ
    -0.07
    igna
    -0.06
    è¯ĬæĸŃåıĬ
    -0.06
    pren
    -0.06
    .Sequence
    -0.06
     Seed
    -0.06
    indu
    -0.06
    çİ
    -0.06
    æķ£åİ»
    -0.06
    uty
    -0.06
    POSITIVE LOGITS
    森
    0.07
    æĬ¼
    0.07
    γοÏħ
    0.07
    æİĴè¡Į
    0.07
    çĤ¹æѤ
    0.07
     priÄį
    0.07
    ÅŁ
    0.07
    å®ıè§Ĥ
    0.07
    ytu
    0.07
    elon
    0.07
    Activations Density 0.006%

    No Known Activations