© 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. 55211
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs

    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
    åı¯ä»¥éĢīæĭ©
    -0.08
    gom
    -0.08
    añ
    -0.08
    壮
    -0.07
    iec
    -0.07
     meiden
    -0.07
    åIJĮæľŁçļĦ
    -0.07
    åı¯ä»¥éģ¸æĵĩ
    -0.07
    åīįè¿°
    -0.07
    .Tasks
    -0.07
    POSITIVE LOGITS
     firsthand
    0.07
    ä¸įä¸ĭåİ»äºĨ
    0.07
    èµ·äºĨ
    0.07
     Patrimonio
    0.06
    é¦ĸåħĪéľĢè¦ģ
    0.06
    以æŃ¤ä¸º
    0.06
    valu
    0.06
    åıĹåĪ°äºĨ
    0.06
     ëĴ¤
    0.06
    äºĭæĥħ
    0.06
    Activations Density 0.015%

    No Known Activations