© 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. 15972
    Prev
    Next
    INDEX
    Explanations

    numbers and math 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
    ofday
    -0.08
    åļ¼
    -0.08
    âŃIJ
    -0.08
    è¡£èįī
    -0.07
    mmc
    -0.07
    داÙĨ
    -0.07
    å¸ĥéĩĮ
    -0.07
    intersect
    -0.07
    tene
    -0.07
    xie
    -0.07
    POSITIVE LOGITS
    eng
    0.06
    ayat
    0.06
    umbo
    0.06
    éĸĵãģ«
    0.06
    æĿ¨æŁ³
    0.06
    sein
    0.06
    engah
    0.06
    è°ģçŁ¥
    0.06
    artal
    0.06
    urada
    0.06
    Activations Density 0.004%

    No Known Activations