© 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. 55192
    Prev
    Next
    INDEX
    Explanations

    II- followed by `-`

    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
    åħ¨éĥ¨è¯Ħ论
    -0.08
    erras
    -0.08
    egur
    -0.08
     Chil
    -0.07
    جÙĪ
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.07
    chini
    -0.07
    hoe
    -0.07
    ibur
    -0.07
     presidency
    -0.07
    POSITIVE LOGITS
    浦
    0.08
    .resource
    0.07
    é¦Ĩ
    0.07
    è¨Ī
    0.06
    ÙĪزÙĩ
    0.06
    ارج
    0.06
    VID
    0.06
    æĸĩæѦ
    0.06
    èĸĩ
    0.06
    åIJĦ家
    0.06
    Activations Density 0.060%

    No Known Activations