© 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. 16055
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with 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
    æѦåĬŁ
    -0.07
    uva
    -0.07
    ullah
    -0.07
    esco
    -0.06
    æĪijçļĦæľĭåıĭ
    -0.06
    iche
    -0.06
    éĸ
    -0.06
    oto
    -0.06
    ä¸Ģ大
    -0.06
    æķ´å¤©
    -0.06
    POSITIVE LOGITS
    ä»ħæѤ
    0.08
     prej
    0.08
    æľīåħ³äººåijĺ
    0.08
    è¦ģ说
    0.07
    ãģ®ãģ¿
    0.07
    åįĥåħĨ
    0.07
    _singular
    0.07
    è®°å¾Ĺ
    0.07
    .mapping
    0.07
     boxe
    0.07
    Activations Density 0.149%

    No Known Activations