© 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. 7236
    Prev
    Next
    INDEX
    Explanations

    "right", "dream", "tolerate", "power", "balance", "exile", "fix", "released"

    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
    nage
    -0.07
    åĴĮä¹īåĬ¡
    -0.06
    λε
    -0.06
     ÙĪرد
    -0.06
    ä¸ĢæĹ¥æ¸¸
    -0.06
    ñar
    -0.06
    uchu
    -0.06
    jub
    -0.06
    oy
    -0.06
    AKE
    -0.06
    POSITIVE LOGITS
    æľīæĪij
    0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.07
     اÙĦØ´ÙĬØ¡
    0.07
    ç»Ĩå°ı
    0.06
    irn
    0.06
    ä»Ģä¹Īåij¢
    0.06
    igne
    0.06
    blad
    0.06
    idge
    0.06
     odnosno
    0.06
    Activations Density 0.109%

    No Known Activations