© 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. 21324
    Prev
    Next
    INDEX
    Explanations

    symbols and slashes

    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
    é«ĺä½İ
    -0.07
    riere
    -0.06
    e
    -0.06
    à¹Ħà¸Ĭ
    -0.06
    es
    -0.06
    borg
    -0.06
    念
    -0.06
    ing
    -0.05
    ç¥ŀä¹ĭ
    -0.05
    s
    -0.05
    POSITIVE LOGITS
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    /from
    0.08
    หาร
    0.08
     Wszyst
    0.08
    ordes
    0.08
     подÑĢазделе
    0.08
    ä¸įå¾Ĺä¸į
    0.08
    åIJĪåIJĮæŶ
    0.08
    ï½ŀãĢį
    0.08
    æ¸ī
    0.08
    Activations Density 0.021%

    No Known Activations