© 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. 44297
    Prev
    Next
    INDEX
    Explanations

    J. Org. Chem

    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
    jaz
    -0.07
    æĹłçĶ¨
    -0.07
    豫
    -0.07
    .Complete
    -0.07
    bior
    -0.06
     Rect
    -0.06
    äºĨä¸ĬæĿ¥
    -0.06
    æĦŁåıĹåĴĮ
    -0.06
    åĨľæ°ijä¸ĵä¸ļåIJĪä½ľç¤¾
    -0.06
    åIJ«éĩij
    -0.06
    POSITIVE LOGITS
    çĴĢ
    0.08
    å®Ĺ
    0.08
    rips
    0.08
    monds
    0.07
    èĢģå®ŀ
    0.07
    verg
    0.07
    巡游
    0.07
    دÙĬÙĩ
    0.07
    catalog
    0.07
    (run
    0.06
    Activations Density 0.051%

    No Known Activations