© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    age and duration

    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
    以èĩ´
    -0.08
    çĶ¨ä»¥
    -0.07
    使ä¹ĭ
    -0.07
     Europas
    -0.07
     Darling
    -0.07
    dess
    -0.07
    以èĩ³äºİ
    -0.07
    ени
    -0.07
    .band
    -0.06
    `](
    -0.06
    POSITIVE LOGITS
    nows
    0.08
    ä¸įåħ¥
    0.08
    çļĦèıľ
    0.07
    velt
    0.07
    ocale
    0.06
    ucht
    0.06
    æĸ°åħī
    0.06
    ervis
    0.06
    ä¸ŃåĽ½ä¼łç»Ł
    0.06
    oard
    0.06
    Activations Density 0.136%

    No Known Activations