© 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. 15882
    Prev
    Next
    INDEX
    Explanations

    missing information, lacking, not supplied

    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
    ä¼įå¾·
    -0.07
    éĶĻè§ī
    -0.07
    -counter
    -0.07
    _blocking
    -0.07
    IGHLIGHT
    -0.07
    ä¼į
    -0.07
    _executor
    -0.07
     اÙĦتÙĨ
    -0.07
    undo
    -0.07
    igest
    -0.07
    POSITIVE LOGITS
     missing
    0.14
    缺失
    0.13
     Missing
    0.12
    缺
    0.12
    Missing
    0.12
    missing
    0.11
    _missing
    0.11
    缺å°ij
    0.11
    缺ä¹ı
    0.10
     lacking
    0.10
    Activations Density 0.161%

    No Known Activations