© 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. 37577
    Prev
    Next
    INDEX
    Explanations

    note that / :

    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
    apesh
    -0.07
    leven
    -0.07
    åIJ»
    -0.07
    å°±åºĶ该
    -0.07
    pear
    -0.07
    rending
    -0.06
    æľīéĴĪ对æĢ§
    -0.06
    errick
    -0.06
    éĨĽ
    -0.06
    å¹²èĦĨ
    -0.06
    POSITIVE LOGITS
    注æĦıçļĦæĺ¯
    0.20
    éľĢè¦ģ注æĦıçļĦæĺ¯
    0.18
     note
    0.17
    è¦ģ注æĦıçļĦæĺ¯
    0.17
    注æĦı
    0.16
    éľĢ注æĦı
    0.16
    note
    0.15
    请注æĦı
    0.15
     Note
    0.15
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.15
    Activations Density 0.212%

    No Known Activations