© 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. 45864
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¹ĭé£İ
    -0.08
    æ½®
    -0.08
    ingt
    -0.07
    sdale
    -0.07
    ä¹ĭä¸ĢçļĦ
    -0.07
    olos
    -0.07
    ä¹ĭæĺŁ
    -0.07
    itemap
    -0.07
    溪éķĩ
    -0.06
     unused
    -0.06
    POSITIVE LOGITS
    -automatic
    0.08
    èĥ
    0.07
    azza
    0.07
    urope
    0.07
    posed
    0.07
    utow
    0.07
    PropertyName
    0.07
    åݲ
    0.07
    èĨĬ
    0.07
    DED
    0.06
    Activations Density 0.000%

    No Known Activations