© 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. 15913
    Prev
    Next
    INDEX
    Explanations

    bicycle and cycling

    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
    çĤĸ
    -0.07
    æıĴæīĭ
    -0.06
     block
    -0.06
     blockbuster
    -0.06
    æīĵçīĮ
    -0.06
    iment
    -0.06
    åī§éĻ¢
    -0.06
    è¿ĪçĿĢ
    -0.06
    å¼Ģ车
    -0.06
     Batch
    -0.06
    POSITIVE LOGITS
    蹬
    0.11
    éªijè¡Į
    0.10
    bike
    0.10
    éªij
    0.09
    å¾Ĵ
    0.09
    à¸Īัà¸ģรยาà¸Ļ
    0.09
    andle
    0.09
     вело
    0.09
    é¨İ士
    0.09
     bike
    0.09
    Activations Density 0.109%

    No Known Activations