© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63938
    Prev
    Next
    INDEX
    Explanations

    homogeneous

    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
    èļ£
    -0.08
    wards
    -0.08
     volna
    -0.08
    ÏĨοÏĤ
    -0.07
    fulness
    -0.07
    leton
    -0.07
    enberg
    -0.07
    ä¸Ģä¼Ĺ
    -0.07
    agger
    -0.06
    ingkatan
    -0.06
    POSITIVE LOGITS
    elay
    0.10
     Äijặn
    0.10
    ality
    0.10
    bred
    0.10
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.10
    ously
    0.09
    à¥įह
    0.09
    estead
    0.09
    моÑĤ
    0.09
    emente
    0.09
    Activations Density 0.018%

    No Known Activations