© 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. 18317
    Prev
    Next
    INDEX
    Explanations

    interrogative words

    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
    umbo
    -0.07
    emen
    -0.07
    jem
    -0.07
    åįĬ个
    -0.07
    apsed
    -0.07
    uffer
    -0.07
    hof
    -0.07
    ål
    -0.07
    ropy
    -0.06
    第äºĮè½®
    -0.06
    POSITIVE LOGITS
    å¹²èĦĨ
    0.07
    /rfc
    0.07
    åIJįæĢĿ
    0.07
    quila
    0.07
    #error
    0.07
     somehow
    0.07
    [System
    0.07
    姥
    0.07
    ä»Ģä¹ĪæĦıæĢĿ
    0.07
    æł¹æľ¬å°±
    0.07
    Activations Density 0.023%

    No Known Activations