© 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. 50112
    Prev
    Next
    INDEX
    Explanations

    value lower than expected

    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
     Gio
    -0.07
    Half
    -0.07
    oor
    -0.07
     mula
    -0.06
    half
    -0.06
    à¸ķาà¸ģ
    -0.06
    ÏģÏĮ
    -0.06
    ADO
    -0.06
     Half
    -0.06
     half
    -0.06
    POSITIVE LOGITS
    ä¸į管
    0.10
     anywhere
    0.09
    ä»»æĦı
    0.09
    åĵªæĢķ
    0.09
    æĹłè®º
    0.09
    ä»»ä½ķäºĭæĥħ
    0.09
    ãģĭãģ¤
    0.09
     EITHER
    0.09
     irrespective
    0.09
    éĢıçĿĢ
    0.08
    Activations Density 0.003%

    No Known Activations