© 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. 55231
    Prev
    Next
    INDEX
    Explanations

    `$` followed by number or colon

    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
    ÙĪÛĮÙĩ
    -0.07
    çª
    -0.07
    üb
    -0.07
    å¾Ĺ人
    -0.07
    椿
    -0.06
    ä½İ级
    -0.06
    è´±
    -0.06
    éij½
    -0.06
    ÑĦан
    -0.06
    ellent
    -0.06
    POSITIVE LOGITS
    ç¨įå¾®
    0.07
    åĭī强
    0.07
    itzer
    0.07
    unded
    0.07
     Terr
    0.07
    emann
    0.07
    é¢ĺ缮çļĦ
    0.07
    áĢĶáĢºáĢ¸
    0.07
     offer
    0.07
    客æĪ·çļĦéľĢæ±Ĥ
    0.07
    Activations Density 0.005%

    No Known Activations