© 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. 55365
    Prev
    Next
    INDEX
    Explanations

    writer assignment directly

    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
    os
    -0.06
    ijs
    -0.06
    ä»»åħį
    -0.06
     symbol
    -0.06
    hren
    -0.06
     Fish
    -0.06
    é£İ度
    -0.06
    zer
    -0.06
    تÙħا
    -0.06
    eo
    -0.06
    POSITIVE LOGITS
    arz
    0.09
    -src
    0.08
    .XML
    0.08
    ÃŃnc
    0.07
    arih
    0.07
    imiter
    0.07
    èµĦæºIJ
    0.07
    èĸĩ
    0.07
    cident
    0.07
    imore
    0.07
    Activations Density 0.002%

    No Known Activations