© 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. 41763
    Prev
    Next
    INDEX
    Explanations

    arrays

    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
     "%"
    -0.08
    terer
    -0.07
    ä¹Łä¸įéľĢè¦ģ
    -0.07
     upside
    -0.06
     Reverse
    -0.06
    ä¸įåĪĨ
    -0.06
    ä»°
    -0.06
    çİĩ
    -0.06
    Reverse
    -0.06
     reverse
    -0.06
    POSITIVE LOGITS
    建设æĪIJ为
    0.08
    ç»Ħç»ĩèĢħ
    0.08
    åĪ©æĸ¯
    0.08
    大åıij
    0.08
     Vacances
    0.08
    æĢ¨
    0.07
    éĽĨä½ĵçļĦ
    0.07
    ình
    0.07
    Че
    0.07
     sinc
    0.07
    Activations Density 0.002%

    No Known Activations