© 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. 55120
    Prev
    Next
    INDEX
    Explanations

    court, yr, machine, sessions, school

    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
    izio
    -0.08
    äºĶåĪĨ
    -0.07
    away
    -0.07
    ëŀµ
    -0.07
     peine
    -0.06
     Kebudayaan
    -0.06
    à¹īà¸Ńà¸Ļ
    -0.06
    hint
    -0.06
    izi
    -0.06
     Cald
    -0.06
    POSITIVE LOGITS
    çĦ¶åIJİå°Ĩ
    0.12
    çĦ¶åIJİåĨį
    0.12
    çĦ¶åIJİ
    0.12
    çĦ¶åIJİåľ¨
    0.12
     rá»ĵi
    0.11
     puis
    0.11
    çĦ¶åIJİå°±
    0.11
    çĦ¶åIJİéĢļè¿ĩ
    0.11
    çĦ¶å¾Į
    0.11
    çĦ¶åIJİæł¹æį®
    0.10
    Activations Density 0.188%

    No Known Activations