© 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. 7028
    Prev
    Next
    INDEX
    Explanations

    compute nodes or code portion

    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
    ç¾İ人
    -0.06
    æĺŃ
    -0.06
    åĭĴ
    -0.06
    ä¸įå½±åĵį
    -0.06
    ä¸įèĩ³
    -0.06
    skr
    -0.06
    irement
    -0.06
    ä¸ĵ项治çIJĨ
    -0.06
    åĽ¾è§£
    -0.06
     Im
    -0.06
    POSITIVE LOGITS
    主ä½ĵ
    0.10
    æľ¬èº«
    0.10
     core
    0.10
    æł¸å¿ĥ
    0.10
    æŃ£æĸĩ
    0.09
    core
    0.09
     itself
    0.09
    åıĬæľīåħ³
    0.09
    idel
    0.09
     اصÙĦÛĮ
    0.09
    Activations Density 0.573%

    No Known Activations