© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10303
    Prev
    Next
    INDEX
    Explanations

    first up or first of all

    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
    kaus
    -0.09
    achine
    -0.08
    娥
    -0.08
    åIJİåĽł
    -0.08
    éĢĤ度
    -0.08
    ä»İèĢĮ导èĩ´
    -0.08
     serupa
    -0.07
    åIJĮæŶå°Ĩ
    -0.07
    åIJ¦åĪĻä¼ļ
    -0.07
    å¿ħè¦ģæŶ
    -0.07
    POSITIVE LOGITS
    leyen
    0.07
     maybe
    0.07
    æĿ¥çľĭ
    0.07
    æıIJåĪ°çļĦ
    0.06
    ç«ĭå¿Ĺ
    0.06
    ç¿
    0.06
    gle
    0.06
    alti
    0.06
     puzz
    0.06
    æīĢæľīçļĦ
    0.06
    Activations Density 0.002%

    No Known Activations