© 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. 20658
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
    ovah
    -0.08
    plex
    -0.07
    IDD
    -0.07
    ilogue
    -0.07
    epak
    -0.07
    cie
    -0.07
    vet
    -0.07
    èĭ¥å¹²æĦıè§ģ
    -0.07
    西éŨ
    -0.07
    ruÄį
    -0.07
    POSITIVE LOGITS
    kler
    0.07
    unden
    0.07
    ynu
    0.07
     Lester
    0.07
    æĺ¯äººç±»
    0.07
    kÄĻ
    0.07
    ä¸įæķ£
    0.06
    .measure
    0.06
    §
    0.06
     Flash
    0.06
    Activations Density 0.006%

    No Known Activations