© 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. 48491
    Prev
    Next
    INDEX
    Explanations

    labeling by numeral and number

    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
    æij¸äºĨ
    -0.07
    åĨįæľī
    -0.06
    æĹłäºĭ
    -0.06
     Shed
    -0.06
    lops
    -0.06
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.06
    åĨħåľ¨
    -0.06
    urb
    -0.06
    ness
    -0.06
     volta
    -0.06
    POSITIVE LOGITS
    ä¸ĩå²ģ
    0.09
    ÑģовеÑģÑĤ
    0.09
    ostringstream
    0.09
    ÐľÐļ
    0.09
    ABCDEFG
    0.09
    éķ¿éĿĴ
    0.08
    ä¾Ŀ次为
    0.08
    oftware
    0.08
    unjuk
    0.08
     numbering
    0.08
    Activations Density 0.023%

    No Known Activations