© 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. 14212
    Prev
    Next
    INDEX
    Explanations

    mathematical calculus expressions

    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
    åIJİèĢħ
    -0.07
     onActivityResult
    -0.07
    teras
    -0.06
    mara
    -0.06
    éĶ¦æłĩ
    -0.06
    /rest
    -0.06
     latter
    -0.06
    heits
    -0.06
    inari
    -0.06
    teur
    -0.06
    POSITIVE LOGITS
    åıĮæĸ¹
    0.08
    åı²å¯Ĩæĸ¯
    0.08
    åħ³ç³»
    0.07
    ivet
    0.07
    æ½Ń
    0.07
    relationships
    0.07
    æĪijæĢİä¹Ī
    0.07
    енок
    0.07
    åıĮæĸ¹åľ¨
    0.07
    åħ³ç³»çļĦ
    0.07
    Activations Density 0.006%

    No Known Activations