© 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. 46508
    Prev
    Next
    INDEX
    Explanations

    code snippets with arithmetic operations

    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
    ãģĺãĤģ
    -0.07
    ufen
    -0.07
    pens
    -0.07
    æĿ¥æĦĪ
    -0.07
    LM
    -0.07
    ë°ĸìĹIJ
    -0.07
    Spo
    -0.06
    allo
    -0.06
    å®Ĺ主
    -0.06
    дÑĢеÑģ
    -0.06
    POSITIVE LOGITS
     scaled
    0.11
    éĻ¤ä»¥
    0.11
    ä¹ĺ以
    0.10
     converted
    0.09
     multiplied
    0.09
    æĬĺç®Ĺ
    0.09
    çļĦä¸ĢåįĬ
    0.09
    scaled
    0.08
    åįĬ个
    0.08
    ä¸ĢåįĬ
    0.08
    Activations Density 0.167%

    No Known Activations