© 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. 59805
    Prev
    Next
    INDEX
    Explanations

    citation 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
    Negative Logits
    anmar
    -0.08
    ä¸įå°±æĺ¯
    -0.08
     malad
    -0.07
    ÑĢие
    -0.07
    æł¹æľ¬å°±
    -0.07
    á»ħn
    -0.07
     jull
    -0.07
    fur
    -0.07
    .bz
    -0.07
    ее
    -0.07
    POSITIVE LOGITS
    Âł
    0.15
     Âł
    0.09
    ³³
    0.09
    âĢ
    0.09
    ³³³
    0.08
    âĢ¹
    0.08
     Âł Âł
    0.07
    ######
    0.07
    <\/
    0.07
    à¸ļรร
    0.07
    Activations Density 1.407%

    No Known Activations