© 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. 46486
    Prev
    Next
    INDEX
    Explanations

    greater than or less than

    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
    Pager
    -0.06
    ärke
    -0.06
    ä¸įåħį
    -0.06
    agate
    -0.06
    ä¸įæİĴéĻ¤
    -0.06
    ook
    -0.06
     prod
    -0.06
    æľĢåĸľæ¬¢
    -0.06
    cono
    -0.06
    conte
    -0.06
    POSITIVE LOGITS
    大äºİ
    0.13
    å°ıäºİ
    0.11
    为éĿŀ
    0.10
    ä½İäºİ
    0.10
    é«ĺäºİ
    0.10
     greater
    0.10
     (>
    0.09
    _greater
    0.09
     (<
    0.09
    GreaterThan
    0.09
    Activations Density 0.039%

    No Known Activations