© 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. 7046
    Prev
    Next
    INDEX
    Explanations

    post on

    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
    me
    -0.07
    祥
    -0.07
    æµħæµħ
    -0.06
    -0.06
    endam
    -0.06
     se
    -0.06
    åĴĮæıIJé«ĺ
    -0.06
    ion
    -0.05
     Her
    -0.05
    erk
    -0.05
    POSITIVE LOGITS
    代表çļĦ
    0.09
    _define
    0.09
    大鱼
    0.08
    alize
    0.08
    velt
    0.08
    _representation
    0.08
    athom
    0.08
    ilian
    0.08
    代表
    0.08
    ról
    0.08
    Activations Density 0.007%

    No Known Activations