© 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. 40150
    Prev
    Next
    INDEX
    Explanations

    explaining a role or task

    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
     سرا
    -0.07
    ä»»ä½ķä¿Ŀè¯ģ
    -0.07
    _cores
    -0.07
    åıijçİ°èĩªå·±
    -0.07
    åѦèĢĮ
    -0.07
    çĭ©
    -0.07
    ällen
    -0.07
    主åĬ¨åIJij
    -0.07
    [out
    -0.07
    æĬĺä¸į
    -0.07
    POSITIVE LOGITS
    etting
    0.07
    ÌĢ
    0.07
     facilit
    0.07
    หย
    0.07
    OI
    0.07
    mid
    0.07
    od
    0.06
    ãĤ»ãĤ¤
    0.06
    \v
    0.06
    croft
    0.06
    Activations Density 0.004%

    No Known Activations