© 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. 18167
    Prev
    Next
    INDEX
    Explanations

    numbers and words like 'again'

    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
    uban
    -0.08
    ç²¾è¯ļ
    -0.07
    _DEAD
    -0.07
     Keg
    -0.07
     تÙĦا
    -0.06
    .shift
    -0.06
    enhagen
    -0.06
    stech
    -0.06
     Duarte
    -0.06
    obble
    -0.06
    POSITIVE LOGITS
     again
    0.12
    again
    0.11
     Again
    0.11
    åıĪä¸Ģ次
    0.10
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.10
    Again
    0.10
    åIJĮæł·çļĦ
    0.09
    à¹Ģหมืà¸Ńà¸Ļà¸ģัà¸Ļ
    0.09
    åıĪæĺ¯ä¸Ģ
    0.09
     nuevamente
    0.08
    Activations Density 0.015%

    No Known Activations