© 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. 622
    Prev
    Next
    INDEX
    Explanations

    controlled variables and studies

    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
    ossi
    -0.10
    nav
    -0.08
    éļĻ
    -0.08
     Terminal
    -0.07
    endar
    -0.07
    主è¦ģ表çݰ为
    -0.07
    ιÏİ
    -0.07
    Terminal
    -0.07
    izzo
    -0.07
    mah
    -0.07
    POSITIVE LOGITS
    å®ŀéªĮ
    0.12
     experiment
    0.12
    åıĺéĩı
    0.12
    å®ŀéªĮä¸Ń
    0.12
     experimental
    0.11
     controlled
    0.11
     variables
    0.11
    controlled
    0.10
    è¯ķéªĮ
    0.10
    çݯå¢ĥåıĺéĩı
    0.10
    Activations Density 0.014%

    No Known Activations