© 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. 32573
    Prev
    Next
    INDEX
    Explanations

    Argentine games

    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
    imeo
    -0.08
    मान
    -0.08
    åĬ¨èĦī硬åĮĸ
    -0.08
    ]-$
    -0.08
    èĮĥæĸĩç½ij
    -0.08
    -google
    -0.08
    -navbar
    -0.08
    æ³ķå¾ĭ声æĺİ
    -0.07
    -get
    -0.07
    asca
    -0.07
    POSITIVE LOGITS
     patient
    0.07
    WR
    0.07
    æĤ£èĢħ
    0.06
    .apply
    0.06
    éħį
    0.06
    ç¥ŀå±±
    0.06
    ä»
    0.06
    aré
    0.06
    对æĤ£èĢħ
    0.06
     Reh
    0.06
    Activations Density 8.043%

    No Known Activations