© 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. 23772
    Prev
    Next
    INDEX
    Explanations

    boredom and slowness

    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
    ikh
    -0.07
     cautiously
    -0.07
     cautious
    -0.07
    iki
    -0.06
    xe
    -0.06
    çĪ±æĬ¤
    -0.06
     protecting
    -0.06
    bold
    -0.06
    itive
    -0.06
    -runtime
    -0.06
    POSITIVE LOGITS
    æĹłèģĬ
    0.18
     boredom
    0.16
    ä¹ıåij³
    0.16
    空èĻļ
    0.16
    åįķè°ĥ
    0.15
    æŀ¯çĩ¥
    0.15
     monot
    0.14
    空æ´ŀ
    0.13
     bored
    0.13
    ä¹ı
    0.13
    Activations Density 0.270%

    No Known Activations