© 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. 4891
    Prev
    Next
    INDEX
    Explanations

    dimensions or internal spaces

    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
    åĨĴ
    -0.08
    erator
    -0.08
     presum
    -0.07
    iat
    -0.07
     contest
    -0.07
    onel
    -0.07
    ctal
    -0.07
    _BODY
    -0.07
     Maver
    -0.07
     contests
    -0.07
    POSITIVE LOGITS
    pace
    0.08
    åĥ»
    0.07
    ää
    0.07
    å°ıéģĵ
    0.07
    走好
    0.07
    èĿĩ
    0.07
    å®ļåIJij
    0.07
     Dimensions
    0.07
    éĨĴæĿ¥
    0.07
    _CONFIGURATION
    0.07
    Activations Density 0.007%

    No Known Activations