© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    is considered

    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
    éĥ½æ¯Ķ
    -0.08
    ÑĦеÑĢ
    -0.08
    ignet
    -0.07
    pal
    -0.07
    صد
    -0.07
    ÙĬدÙĬ
    -0.07
    idler
    -0.07
    (Abstract
    -0.07
    à¹Īà¸Ńà¸Ļ
    -0.07
     hypothetical
    -0.06
    POSITIVE LOGITS
    ä¸įå±ŀäºİ
    0.16
    å±ŀäºİ
    0.13
     belongs
    0.12
    ä¸įå½Ĵ
    0.11
     belong
    0.11
    å½Ĵå±ŀäºİ
    0.11
     belonged
    0.11
     separate
    0.11
    å½Ĵå±ŀ
    0.11
    éĥ½å±ŀäºİ
    0.11
    Activations Density 0.093%

    No Known Activations