© 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. 47458
    Prev
    Next
    INDEX
    Explanations

    sequences and equations

    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
     목
    -0.08
    umon
    -0.07
    å¯¹æľ¬æ¬¡
    -0.07
    éľĢè¦ģåIJĮ
    -0.07
    strt
    -0.07
    IONI
    -0.07
    çİĭæľĿ
    -0.07
    çļĦè¯Ħä»·æĺ¯
    -0.07
    icitÃł
    -0.07
    heur
    -0.07
    POSITIVE LOGITS
     kond
    0.07
    çİĽçijĻ
    0.07
    äºĨ解èĩªå·±çļĦ
    0.07
    YM
    0.06
    åѦåı²
    0.06
    ä¹IJä¹İ
    0.06
    Gu
    0.06
    (formatter
    0.06
    æľīäºĽäºĭ
    0.06
    çĻ¾éĩĮ
    0.06
    Activations Density 0.025%

    No Known Activations