© 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. 613
    Prev
    Next
    INDEX
    Explanations

    connecting disparate things

    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
    åij¤
    -0.08
    éļı
    -0.08
    å°¼åı¤
    -0.07
    itoriale
    -0.07
    обен
    -0.07
    еÑģÑĤо
    -0.07
    ulina
    -0.07
    roup
    -0.07
    对èĩªå·±
    -0.07
     Nordest
    -0.07
    POSITIVE LOGITS
     seamlessly
    0.12
    çļĦæ¡¥æ¢ģ
    0.12
     disparate
    0.11
     brid
    0.11
     bridges
    0.10
     bridge
    0.10
    è´¯éĢļ
    0.10
    bridge
    0.10
    æ¡¥æ¢ģ
    0.09
     Bridge
    0.09
    Activations Density 0.180%

    No Known Activations