© 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. 49903
    Prev
    Next
    INDEX
    Explanations

    k, n, m, R, a as variables

    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
    西åİ¿
    -0.08
    ippet
    -0.07
    ä¸Ĭä¸ĢæĿ¡
    -0.07
    yek
    -0.07
    åŃ¦ä»¥èĩ´
    -0.07
    ully
    -0.07
    yton
    -0.07
    _HOOK
    -0.07
    eley
    -0.07
    пÑĢÑı
    -0.07
    POSITIVE LOGITS
    éĻIJ
    0.07
    nc
    0.07
     multi
    0.07
    çĻ»å½ķæŁ¥çľĭ
    0.07
    ç¶Ń
    0.07
     numRows
    0.07
    :num
    0.07
    人æķ°
    0.07
    æ¯ıç»Ħ
    0.07
    awn
    0.07
    Activations Density 0.011%

    No Known Activations