© 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. 17443
    Prev
    Next
    INDEX
    Explanations

    rotary cone

    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
    tim
    -0.06
    çļĭ
    -0.06
    交äºĨ
    -0.06
    ÑģÑĤал
    -0.06
    æīįä¸įä¼ļ
    -0.06
    å³»
    -0.06
    ä¸įä¼ļåĨį
    -0.06
    çĵ·
    -0.06
    _tim
    -0.06
    å¼Ł
    -0.06
    POSITIVE LOGITS
    éĩı大
    0.08
    otar
    0.07
    ihan
    0.07
    端çļĦ
    0.07
    меÑģÑĤи
    0.07
    idUser
    0.07
    åľ¨çľī
    0.07
    zyw
    0.07
    born
    0.07
    REM
    0.07
    Activations Density 0.611%

    No Known Activations