© 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. 19360
    Prev
    Next
    INDEX
    Explanations

    numbers and constructs

    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
    DMI
    -0.08
    ç¯Ħ
    -0.08
    缮åīįæŃ£åľ¨
    -0.08
    à¤ķारà¥Ģ
    -0.07
    æĸ°å¤©åľ°
    -0.07
    é¡¹çĽ®åıĬ
    -0.07
    太åı¤
    -0.07
    .Suppress
    -0.07
    å¨ĵ
    -0.07
    ØŃØ©
    -0.07
    POSITIVE LOGITS
    çļĦåıĮéĩį
    0.11
    æĹ¢åı¯ä»¥
    0.11
    Dual
    0.10
    åıĮéĩį
    0.10
     dual
    0.10
     ambigu
    0.09
    åIJĮä¸Ģ个
    0.09
     Dual
    0.09
    å·¦åı³
    0.09
     дваждÑĭ
    0.09
    Activations Density 0.197%

    No Known Activations