© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation and speech verbs

    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
    åİĨåİĨ
    -0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    à¤ļित
    -0.07
    ä½¼
    -0.07
    æĥħä¸įèĩªç¦ģ
    -0.07
    åıĪæĢķ
    -0.07
    enville
    -0.07
    æĥĬéŃĤ
    -0.07
    æľīåħ³äºĭ项
    -0.07
    秫
    -0.07
    POSITIVE LOGITS
    åıį驳
    0.10
    对äºİè¿ĻäºĽ
    0.08
    éĹ»è¨Ģ
    0.08
     replies
    0.08
    æģ°æģ°
    0.08
    PLY
    0.08
    _counters
    0.07
     countered
    0.07
    åIJ¬çĿĢ
    0.07
    åĽŀçŃĶ说
    0.07
    Activations Density 0.121%

    No Known Activations