© 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. 30072
    Prev
    Next
    INDEX
    Explanations

    prepared ahead of time

    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
    åIJĮæŶè¿ĺè¦ģ
    -0.07
    èĸĩ
    -0.07
    毫
    -0.07
    è¦ģ强åĮĸ
    -0.06
    ogo
    -0.06
     Brem
    -0.06
    顺
    -0.06
     eg
    -0.06
    éłĨ
    -0.06
    bor
    -0.06
    POSITIVE LOGITS
    é¢ĦåħĪ
    0.12
     заÑĢанее
    0.10
    ลà¹Īวà¸ĩหà¸Ļà¹īา
    0.10
     미리
    0.10
    é¢Ħä»ĺ
    0.10
     beforehand
    0.10
     offline
    0.10
     upfront
    0.10
    éĿĻæĢģ
    0.10
    azon
    0.09
    Activations Density 0.093%

    No Known Activations