© 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. 37773
    Prev
    Next
    INDEX
    Explanations

    programming keywords and technical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģæĭį
    -0.08
    esion
    -0.07
    ÑĨеле
    -0.07
    odle
    -0.07
    好äºĭ
    -0.07
    æĿİ家
    -0.06
    åį«åĽ½
    -0.06
    REAM
    -0.06
    ream
    -0.06
    elp
    -0.06
    POSITIVE LOGITS
     famously
    0.08
    èijĹåIJįçļĦ
    0.08
     famous
    0.07
    ippets
    0.07
    lator
    0.07
    atoire
    0.07
     infamous
    0.07
    å±ķå¼ĢäºĨ
    0.07
    åīª
    0.07
    .ogg
    0.07
    Activations Density 0.236%

    No Known Activations