© 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. 48321
    Prev
    Next
    INDEX
    Explanations

    text file line separators

    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
    amenta
    -0.09
    akes
    -0.08
    çĶ¨æĪ·çļĦéľĢæ±Ĥ
    -0.08
    ÄĻż
    -0.08
    åįģç«ł
    -0.07
    çļĦèĤ©èĨĢ
    -0.07
    å®īæģ¯
    -0.07
    主é¢ĺåħļ
    -0.07
    管çIJĨæ³ķ
    -0.07
    游离
    -0.07
    POSITIVE LOGITS
    èĵ
    0.07
    etten
    0.07
    еÑĢÑĮ
    0.06
    åĪ»
    0.06
    arne
    0.06
    anker
    0.06
     nhiên
    0.06
    retty
    0.06
    殿ä¸ĭ
    0.06
    à¹Ģà¸Ķียว
    0.06
    Activations Density 0.003%

    No Known Activations