© 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. 642
    Prev
    Next
    INDEX
    Explanations

    residue analysis and reserves

    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
     Pesso
    -0.09
    enticate
    -0.09
    ãĤīãģĭ
    -0.09
    itudes
    -0.09
    oriously
    -0.09
    Ø´ÙĬØ©
    -0.08
    reja
    -0.08
    entifier
    -0.08
    èµĦæºIJç½ij
    -0.08
    ืà¸Ļ
    -0.08
    POSITIVE LOGITS
    ä¸įæĭĶ
    0.10
    guardo
    0.10
    ponsible
    0.10
    ponde
    0.09
    ponce
    0.09
    ponder
    0.08
    angler
    0.08
    pective
    0.08
    à¸Ĭาà¸ķิ
    0.08
    ervoir
    0.08
    Activations Density 0.133%

    No Known Activations