© 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. 34747
    Prev
    Next
    INDEX
    Explanations

    people attending events

    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
    æĺ¯ä¸Ģåľº
    -0.08
    æĺ¯æĬĬ
    -0.08
    æĪijèĩªå·±
    -0.08
    sell
    -0.07
    áĥĵáĥĶ
    -0.07
    iegend
    -0.07
    åĪ°å°¾
    -0.07
    ÐĶУ
    -0.07
     ës
    -0.07
    ä¸Ń磩
    -0.07
    POSITIVE LOGITS
    edia
    0.09
    æĪĸä¸į
    0.08
    åºĶè¿IJèĢĮçĶŁ
    0.07
     (?)
    0.07
    ï¼Ī
    0.07
    (?)
    0.07
    èĢĮä¸Ķè¿ĺæĺ¯
    0.07
    æĪĸå°ij
    0.07
    (
    0.07
    ä¸ĵä¸ļä»İäºĭ
    0.07
    Activations Density 0.498%

    No Known Activations