© 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. 4258
    Prev
    Next
    INDEX
    Explanations

    array initialization

    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
    S
    -0.07
    ç¯Ŀ
    -0.07
    it
    -0.06
    符
    -0.06
    ä»ĸ们
    -0.06
    ä»ĸ们æľī
    -0.06
    uer
    -0.06
    upo
    -0.06
    using
    -0.06
    in
    -0.06
    POSITIVE LOGITS
    ForRow
    0.09
    ambang
    0.08
    lav
    0.08
    åľĴ
    0.08
    ektor
    0.08
    lian
    0.08
    cioni
    0.08
    æķĻå¾Ĵ
    0.08
    istique
    0.08
    $headers
    0.08
    Activations Density 0.004%

    No Known Activations