© 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. 57507
    Prev
    Next
    INDEX
    Explanations

    arthroplasty, arthralgia, arctan, ar

    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
    翼翼
    -0.11
    áĥ£áĥłáĥĺ
    -0.10
    ANNER
    -0.08
    еÑĢна
    -0.08
    à¸Ĺà¹Į
    -0.07
    ãģĦãĤĭ
    -0.07
    iard
    -0.07
    à¸Ľà¸±à¸ĩ
    -0.07
    ioneer
    -0.07
    MBOL
    -0.07
    POSITIVE LOGITS
    er
    0.08
    ar
    0.08
    éns
    0.08
    atan
    0.07
    arit
    0.07
    erp
    0.07
    idium
    0.07
    appa
    0.07
    ness
    0.07
    å¹´çļĦæŶåĢĻ
    0.07
    Activations Density 0.008%

    No Known Activations