© 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. 546
    Prev
    Next
    INDEX
    Explanations

    medium

    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
    bamos
    -0.09
    ãĤĪãģĨãģª
    -0.08
    abelle
    -0.08
    enberg
    -0.08
    enburg
    -0.08
    ython
    -0.08
    elet
    -0.08
    ếm
    -0.07
    ÙħÙĬÙħ
    -0.07
    AnimationFrame
    -0.07
    POSITIVE LOGITS
    åĨį说äºĨ
    0.08
    ized
    0.08
    à¹Ħหรà¹Ī
    0.08
     اÙĦØŃاÙĦ
    0.08
    reetings
    0.08
    jenigen
    0.08
    ipse
    0.07
    inary
    0.07
    ellaneous
    0.07
    çĶŁäº§æĢ»åĢ¼
    0.07
    Activations Density 0.015%

    No Known Activations