© 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. 50611
    Prev
    Next
    INDEX
    Explanations

    calculus and derivatives

    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¦Ĥèį¼
    -0.07
    åħ¨éĥ¨çļĦ
    -0.07
    ura
    -0.07
    ãĥĨãĤ£ãĥ³ãĤ°
    -0.07
    uas
    -0.07
    /null
    -0.07
    两å¸Ĥ
    -0.07
    parg
    -0.06
     ange
    -0.06
    ulan
    -0.06
    POSITIVE LOGITS
    ä¸īçĶŁ
    0.08
    榮
    0.07
    æļ§
    0.07
    åİĨæŶ
    0.07
    ä¼ĺ
    0.07
     Instruments
    0.07
    à¹Ģล
    0.07
    ×ĺ×Ļ×Ŀ
    0.07
    èį£
    0.07
    rotch
    0.06
    Activations Density 0.028%

    No Known Activations