© 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. 16229
    Prev
    Next
    INDEX
    Explanations

    non-round contours

    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
    sä
    -0.09
    oder
    -0.08
    ä¹Łä¸į太
    -0.07
    öd
    -0.07
    olds
    -0.07
    mam
    -0.07
    åĴĮæľĢ
    -0.07
    kest
    -0.07
    odus
    -0.07
    大æľĥ
    -0.07
    POSITIVE LOGITS
    ç»ĿéĿŀ
    0.07
     غÛĮر
    0.07
    ä¸įæŃ»
    0.07
     instead
    0.07
    æīįæľīäºĨ
    0.07
    éĿŀ
    0.07
    æŀľçĦ¶
    0.07
    æĪijä¸įæĺ¯
    0.06
    æĺ¯éĿŀ
    0.06
    elligent
    0.06
    Activations Density 0.443%

    No Known Activations