© 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. 48721
    Prev
    Next
    INDEX
    Explanations

    invention generally

    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
    ä»»æĢ§
    -0.08
    以赴
    -0.08
    ois
    -0.07
    wap
    -0.07
     unthinkable
    -0.07
    ä¿¡æģ¯æĬĢæľ¯æľīéĻIJåħ¬åı¸
    -0.07
    çŃī她
    -0.07
    USTA
    -0.07
    [âĢ¦
    -0.07
    ince
    -0.07
    POSITIVE LOGITS
    %B
    0.07
     '
    0.06
    éĢłçļĦ
    0.06
    leans
    0.06
    çĭ©
    0.06
    ä¹ĭçİĭ
    0.06
    onda
    0.06
    æĸ°çĶŁçļĦ
    0.06
     sight
    0.06
    olid
    0.06
    Activations Density 0.004%

    No Known Activations