© 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. 25741
    Prev
    Next
    INDEX
    Explanations

    buffered input/output

    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
    æĿŀ
    -0.08
    ót
    -0.07
    csrf
    -0.07
    åľ¨åįĬ
    -0.07
    交èŃ¦å¤§éĺŁ
    -0.07
    _PAYLOAD
    -0.07
     devid
    -0.07
    为人们
    -0.07
    WISE
    -0.07
     sire
    -0.07
    POSITIVE LOGITS
    ç¦ı
    0.08
    å¯Ħ
    0.07
    hea
    0.07
    à¸ķิ
    0.07
     Buffered
    0.07
    æľīç¦ı
    0.07
    inho
    0.07
    ideo
    0.06
    buf
    0.06
     forthcoming
    0.06
    Activations Density 0.003%

    No Known Activations