© 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. 2656
    Prev
    Next
    INDEX
    Explanations

    equations containing variables like p, x, y, alpha, and integrals

    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
    åħĭåħ°
    -0.07
    æĸ¯åŁº
    -0.07
    ewn
    -0.07
    utre
    -0.07
    irian
    -0.07
    ltk
    -0.07
    蹦蹦
    -0.07
    rš
    -0.07
    好好åŃ¦ä¹ł
    -0.06
    ERE
    -0.06
    POSITIVE LOGITS
    esson
    0.08
    (begin
    0.07
    issen
    0.07
    hus
    0.07
    ä¸īè§Ĵ
    0.07
    issan
    0.07
     '\
    0.06
    acerb
    0.06
    ä¹Ŀå·ŀ
    0.06
    phys
    0.06
    Activations Density 0.009%

    No Known Activations