© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44540
    Prev
    Next
    INDEX
    Explanations

    size and scale

    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
    Negative Logits
    avar
    -0.07
    æĺ±
    -0.06
    åįĩåħ¥
    -0.06
     Batam
    -0.06
    éĩijæ¦ľ
    -0.06
    æ¯ıæĹ¥ä¸Ģç»ĥ
    -0.06
    æĹłè®ºä½łæĺ¯
    -0.06
     únic
    -0.06
    apres
    -0.06
    BX
    -0.06
    POSITIVE LOGITS
    æŀģéĻIJ
    0.14
    èĩ³æŀģ
    0.12
     Extreme
    0.10
     limite
    0.10
    ä¸įèĥ½åĨį
    0.10
    Extreme
    0.10
     Limits
    0.10
     пÑĢедел
    0.10
    æŀģçĤ¹
    0.10
    ä¸ĭéĻIJ
    0.10
    Activations Density 0.133%

    No Known Activations