© 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. 37513
    Prev
    Next
    INDEX
    Explanations

    cdn.net / pubs

    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
    زاÙĨ
    -0.08
    âĢİ
    -0.08
    صاص
    -0.08
    >:</
    -0.07
    esta
    -0.07
    lyph
    -0.07
    ÑģÑĤвен
    -0.07
    asta
    -0.07
     повеÑĢÑħ
    -0.07
    каÑģ
    -0.07
    POSITIVE LOGITS
    æĭ¨
    0.07
    åıĺæĽ´é¡¹çĽ®
    0.06
    å¦Ĥ约
    0.06
    æµ
    0.06
    举åĿ¡
    0.06
    bruck
    0.06
    -components
    0.06
    romise
    0.06
     rec
    0.06
    iffin
    0.06
    Activations Density 0.217%

    No Known Activations