© 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. 34716
    Prev
    Next
    INDEX
    Explanations

    thanks

    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
     Goed
    -0.07
    æĪĸä¸İ
    -0.07
    Ħ
    -0.07
    okal
    -0.07
    cec
    -0.07
     negatives
    -0.07
    ĥĿ
    -0.07
    /cs
    -0.06
    icians
    -0.06
    pto
    -0.06
    POSITIVE LOGITS
    å½¢èī²
    0.07
    å¿ĺ
    0.07
    datagrid
    0.07
    åIJĦ项è§Ħç«łåĪ¶åº¦
    0.06
    icha
    0.06
    advance
    0.06
     Ùħجد
    0.06
    æģĥ
    0.06
    Kit
    0.06
    ixa
    0.06
    Activations Density 0.214%

    No Known Activations