© 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. 52139
    Prev
    Next
    INDEX
    Explanations

    opening files or templates

    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
    çļĦæ°Ķæ°Ľ
    -0.08
    رد
    -0.08
    æŦ
    -0.07
    enth
    -0.07
    æľīéģĵ
    -0.07
    ving
    -0.07
    iar
    -0.07
    ارة
    -0.07
    æľīè¯Ŀ
    -0.07
    olland
    -0.07
    POSITIVE LOGITS
    udad
    0.09
    resa
    0.07
    åīĤçŃī
    0.06
     el
    0.06
    å°ij
    0.06
    ä¸Ńå¿ĥçŃī
    0.06
    并æĬĬ
    0.06
     Amaz
    0.06
    æľīæīĢ
    0.06
    aian
    0.06
    Activations Density 0.267%

    No Known Activations