© 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. 50519
    Prev
    Next
    INDEX
    Explanations

    end-shaft, output shaft, rear part, lighting circuit

    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
     inquire
    -0.06
     unc
    -0.06
    _visibility
    -0.06
    สห
    -0.05
    öm
    -0.05
    igned
    -0.05
    วà¸Ļ
    -0.05
    æĪ¯
    -0.05
    SETS
    -0.05
    ãģ¸
    -0.05
    POSITIVE LOGITS
    IndexOf
    0.09
    é¾Ļä¹ĭ
    0.08
    çŃ
    0.07
    åĬ¨èĦij
    0.07
    iple
    0.07
    encion
    0.07
    cco
    0.07
     roundup
    0.07
    åıijèĩª
    0.07
     пожал
    0.07
    Activations Density 0.449%

    No Known Activations