© 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. 16427
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES COURT OF APPEALS

    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
    aggi
    -0.08
    zelfde
    -0.08
    foundland
    -0.08
    大åħ¸
    -0.08
    à¯įà®ķ
    -0.08
    èĩ´è¿ľ
    -0.08
    大殿
    -0.08
    ئÙĦ
    -0.08
    nable
    -0.08
    visto
    -0.08
    POSITIVE LOGITS
    uncan
    0.10
     volna
    0.09
    orary
    0.09
    erty
    0.08
    utsche
    0.08
    gow
    0.07
     dÃłng
    0.07
    ors
    0.07
    ä¹Łä¸įæĥ³
    0.07
    'autres
    0.07
    Activations Density 0.002%

    No Known Activations