© 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. 60005
    Prev
    Next
    INDEX
    Explanations

    mathematical/programming terms context

    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
    _BOTH
    -0.08
    å°¼æĸ¯
    -0.07
    jubl
    -0.07
    åIJİæīįèĥ½
    -0.07
    йко
    -0.07
    çĴĢ
    -0.07
    å®Ŀ
    -0.07
    elio
    -0.07
    èIJ½ãģ¨ãģĹ
    -0.06
    åīįæµ·
    -0.06
    POSITIVE LOGITS
    åIJĮ为
    0.08
    ters
    0.07
    åĴĮåĨħ容
    0.07
    ìŀIJìĿ¸
    0.07
    Unnamed
    0.07
    ting
    0.07
    nameof
    0.07
     interessados
    0.07
    åĴĮæĸ¹æ³ķ
    0.07
    rix
    0.06
    Activations Density 0.024%

    No Known Activations