© 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. 47165
    Prev
    Next
    INDEX
    Explanations

    Taylor expansion

    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
    åį³å¢¨
    -0.07
    ingt
    -0.07
     execution
    -0.07
    éĿĴæ¢ħ
    -0.07
    çij
    -0.06
    бÑĢи
    -0.06
    bra
    -0.06
    ond
    -0.06
    ç»Łè®¡å±Ģ
    -0.06
     capture
    -0.06
    POSITIVE LOGITS
     expansion
    0.08
    åIJijæĿ¥
    0.08
    å±Ĥå±Ĥ
    0.08
    adier
    0.07
     Expansion
    0.07
    åºľ
    0.07
    æī©å¼ł
    0.07
     funcs
    0.07
    Expansion
    0.07
     expand
    0.07
    Activations Density 0.003%

    No Known Activations