© 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. 55916
    Prev
    Next
    INDEX
    Explanations

    definition or question separator

    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
    ئ
    -0.08
     (
    -0.08
    ص
    -0.06
    ä»Ķ
    -0.06
    çĻ¾
    -0.06
     ...
    -0.06
    å§Ķ
    -0.06
    æł¹
    -0.06
    -0.06
    欲
    -0.06
    POSITIVE LOGITS
    æĸ½æīĵ
    0.09
    oined
    0.08
    ç¥Ŀç¦ıä½ł
    0.08
    !”.
    0.08
     kors
    0.08
    ajikan
    0.08
    éªģ
    0.08
    oose
    0.08
    ãĢij,
    0.08
    odar
    0.08
    Activations Density 0.006%

    No Known Activations