© 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. 44884
    Prev
    Next
    INDEX
    Explanations

    circular references

    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
     Gara
    -0.08
    jár
    -0.08
    amedi
    -0.08
    годно
    -0.07
    elib
    -0.07
    å¾Īå¤ļä¸ľè¥¿
    -0.07
    artes
    -0.07
    æİ§ç³»ç»Ł
    -0.07
    Ø«ÙĬر
    -0.07
    erguson
    -0.07
    POSITIVE LOGITS
    s
    0.12
    er
    0.11
    nya
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.09
    ly
    0.08
    ities
    0.08
    o
    0.08
    ity
    0.08
    ا
    0.08
    Activations Density 0.004%

    No Known Activations