© 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. 44431
    Prev
    Next
    INDEX
    Explanations

    cue for story or explanation

    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
     ÙĪسÙĦ
    -0.07
    ä¸Ģæ¦Ĥ
    -0.07
     duy
    -0.07
     Gri
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    æľīæĥħ
    -0.06
    if
    -0.06
    ä¸ĢæıIJ
    -0.06
    éľĢè¦ģåħĪ
    -0.06
    没æĶ¶
    -0.06
    POSITIVE LOGITS
    ArrayOf
    0.08
    ANGAN
    0.08
    ertes
    0.08
     finalement
    0.07
    xffffff
    0.07
    ований
    0.07
    æĻ®æ³ķ
    0.07
    ampa
    0.07
    burgh
    0.07
    >".
    0.07
    Activations Density 0.003%

    No Known Activations