© 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. 11566
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

    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
    иÑİ
    -0.08
    ses
    -0.08
    ios
    -0.08
    ç¼Ń
    -0.07
    esi
    -0.07
    rie
    -0.07
     :
    -0.07
    utom
    -0.07
    ÏĥμαÏĦα
    -0.06
    iom
    -0.06
    POSITIVE LOGITS
    bjerg
    0.08
    âĢ¦âĢ¦ãĢĤ
    0.08
    {//
    0.08
    ÑĤин
    0.08
    åijĨ
    0.07
    acular
    0.07
    Õ¡Õ¯Õ¡Õ¶
    0.07
    Õ¡Õ¯
    0.07
    ropolitan
    0.07
    _=
    0.07
    Activations Density 0.070%

    No Known Activations