© 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. 46456
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponentials

    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
    áŁĭ
    -0.08
    ptes
    -0.08
    itário
    -0.08
    ì§ĵ
    -0.07
    ÏĤ
    -0.07
    udeau
    -0.07
    çĶ¨çľ¼
    -0.07
    æĸĮ
    -0.07
     ì§ĵ
    -0.07
    aru
    -0.07
    POSITIVE LOGITS
    agog
    0.07
    ansion
    0.07
    å¯¹æľ¬
    0.07
    ró
    0.07
     Fak
    0.07
    agri
    0.06
    aminer
    0.06
    emplo
    0.06
    -refresh
    0.06
    ä¸įè¡°
    0.06
    Activations Density 0.005%

    No Known Activations