© 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. 54989
    Prev
    Next
    INDEX
    Explanations

    XML structure

    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
    åħ¶èº«
    -0.07
    åĩºåħ¶
    -0.06
    äºĮçŃī
    -0.06
    为æķ°
    -0.06
     khúc
    -0.06
    nat
    -0.06
    ç«ĭäºİ
    -0.06
    end
    -0.06
    sto
    -0.06
     ↵		↵
    -0.06
    POSITIVE LOGITS
    tees
    0.09
     Lic
    0.08
    .functional
    0.08
    æ¬Ħ
    0.08
    heels
    0.08
    tagen
    0.07
    æѧ
    0.07
    ÛĮر
    0.07
    ëĶ
    0.07
    amber
    0.07
    Activations Density 0.004%

    No Known Activations