© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22589
    Prev
    Next
    INDEX
    Explanations

    ignore, omit, leave, handle

    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
    Not in Any Lists

    No Comments

    Negative Logits
    +xml
    -0.07
    oldt
    -0.07
    ERVER
    -0.07
    رص
    -0.07
     bland
    -0.07
     echt
    -0.07
    Ø®ÙĨ
    -0.07
    öl
    -0.07
    æĽ¿è¡¥
    -0.07
    eced
    -0.07
    POSITIVE LOGITS
    ä¸įè°Ī
    0.12
    åıªç®¡
    0.12
    ä¸įèĢĥèĻij
    0.12
    ä¸įéĹ®
    0.11
     ignore
    0.11
    忽çķ¥
    0.10
    .ignore
    0.10
     dealt
    0.10
    Ignore
    0.10
    Deal
    0.10
    Activations Density 0.167%

    No Known Activations