© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29728
    Prev
    Next
    INDEX
    Explanations

    completion or cessation

    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
    æľĪåĩºçĶŁ
    -0.08
    _skip
    -0.08
    ØŃا
    -0.07
    skip
    -0.07
    裸
    -0.06
    cza
    -0.06
    æĦ£
    -0.06
    Skip
    -0.06
    å¼Ģèĥĥ
    -0.06
     mote
    -0.06
    POSITIVE LOGITS
    åģľæŃ¢äºĨ
    0.15
    åģľæŃ¢
    0.14
     cessation
    0.14
    ç»ĵæĿŁäºĨ
    0.14
    ç»ĪæŃ¢
    0.14
    å°±ç»ĵæĿŁäºĨ
    0.14
     stop
    0.13
     пÑĢек
    0.13
     stops
    0.13
    ç»ĵæĿŁ
    0.13
    Activations Density 0.396%

    No Known Activations