© 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. 4713
    Prev
    Next
    INDEX
    Explanations

    managing, management, removal, coat

    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
    对ä¸įåIJĮ
    -0.07
    ean
    -0.06
    íĻĶ
    -0.06
    åıĬæľīåħ³
    -0.06
    andr
    -0.06
    对éĤ£äºĽ
    -0.06
    个ä¸įåģľ
    -0.06
     ìĦ¸ê³ĦìĹIJìĦľ
    -0.06
    éŁ¿
    -0.06
     Uncomment
    -0.06
    POSITIVE LOGITS
    åı£å¤´
    0.08
    以德
    0.07
     via
    0.07
    ={{
    0.07
    _ALIGNMENT
    0.07
    PILE
    0.07
     intim
    0.07
    以ä¸Ģç§į
    0.07
    .override
    0.06
    åºĦ
    0.06
    Activations Density 0.198%

    No Known Activations