© 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. 10554
    Prev
    Next
    INDEX
    Explanations

    type of, genre, classification, called

    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
    太åı¤
    -0.08
    rensa
    -0.08
    inel
    -0.08
    ivec
    -0.07
    æĹ¥æŃ¢
    -0.07
    èĬ±éĥ½
    -0.07
    tene
    -0.07
    åķĨæłĩä¿¡æģ¯
    -0.07
    rens
    -0.07
    tom
    -0.07
    POSITIVE LOGITS
     type
    0.13
    ç±»åŀĭ
    0.13
    ç±»åŀĭçļĦ
    0.11
    type
    0.11
    atype
    0.11
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.11
    ç±»åŀĭ为
    0.11
    é¡ŀåŀĭ
    0.11
    çļĦç±»åŀĭ
    0.11
     classification
    0.10
    Activations Density 0.077%

    No Known Activations