© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2764
    Prev
    Next
    INDEX
    Explanations

    Punjabi, Hindi, or script characters

    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
    æľ¨çĵľ
    -0.07
    æľī好çļĦ
    -0.07
    odel
    -0.07
    yan
    -0.07
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.07
     amount
    -0.07
     “âĢ¦
    -0.06
    ugel
    -0.06
    åĨ²è¿Ľ
    -0.06
    请çĻ»å½ķ
    -0.06
    POSITIVE LOGITS
    wali
    0.07
    éĻ©
    0.07
    è´¢
    0.07
    äºĨåįĬ天
    0.07
    å¯Įè´µ
    0.07
     Bá
    0.07
    enaar
    0.07
    aroo
    0.07
    à¸Ŀ
    0.06
    IgnoreCase
    0.06
    Activations Density 0.006%

    No Known Activations