© 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. 9220
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

    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
    ewise
    -0.07
    èģļ
    -0.07
    essa
    -0.06
     Wilkinson
    -0.06
    yla
    -0.06
    çī¹å·¥
    -0.06
    éĤĢ
    -0.06
    éħį
    -0.06
    à¹Ģหล
    -0.06
    æŀľ
    -0.06
    POSITIVE LOGITS
    eur
    0.08
    orium
    0.08
    illion
    0.08
    ering
    0.08
    orr
    0.07
    çŀ©
    0.07
    ленÑĮ
    0.07
    ганÑĤ
    0.07
    Ùĩاب
    0.07
    enth
    0.07
    Activations Density 0.068%

    No Known Activations