© 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. 30745
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions and calculus

    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
    erma
    -0.07
    hra
    -0.07
    ([{
    -0.07
    åķĨä¸ļçĶ¨éĢĶ
    -0.07
    icl
    -0.07
    anj
    -0.06
    adio
    -0.06
    æĿĢæİī
    -0.06
     sp
    -0.06
    erial
    -0.06
    POSITIVE LOGITS
    ecken
    0.07
    à¸Ľà¸£à¸°à¸Īำวัà¸Ļ
    0.07
    _HELP
    0.07
    èµ·ä¼ı
    0.07
    éĺ¿å¸ĥ
    0.06
    纵è§Ĥ
    0.06
    å¤
    0.06
    åĩºæ²¡
    0.06
    åıĹæĥł
    0.06
    æĬĺãĤĬ
    0.06
    Activations Density 0.002%

    No Known Activations