© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    places and paths

    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
    为天
    -0.06
    okers
    -0.06
    /up
    -0.06
    bnb
    -0.06
    æĹ
    -0.06
    Gu
    -0.06
    èįĶ
    -0.06
    acc
    -0.05
    AZ
    -0.05
     sekali
    -0.05
    POSITIVE LOGITS
    ung
    0.08
    ï¾ŀ
    0.08
    ÃŁen
    0.08
    crição
    0.08
    ë¦ĩ
    0.07
    à¹Īà¸Ńยà¹Īาà¸ĩ
    0.07
    ลฯ
    0.07
    à¯Ī
    0.07
    ä¸ĭåIJĮ
    0.07
    家åºĹ
    0.07
    Activations Density 0.600%

    No Known Activations