© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    industries

    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
    ä¹ĭä¸į
    -0.07
    æĪĸ被
    -0.07
    ®
    -0.07
    åĿIJ
    -0.07
    æĪĸçĶ±
    -0.06
    æĪĸä¸į
    -0.06
    (
    -0.06
    ä»·
    -0.06
    (s
    -0.06
    çŤ
    -0.06
    POSITIVE LOGITS
    çŃīé¢ĨåŁŁ
    0.14
    é¢ĨåŁŁ
    0.12
    çŃīé¢ĨåŁŁçļĦ
    0.12
     ë¶Ħìķ¼ìĹIJìĦľ
    0.11
    éłĺåŁŁ
    0.10
    é¢ĨåŁŁçļĦ
    0.10
    wesen
    0.10
     ë¶Ħìķ¼
    0.09
    é¢ĨåŁŁä¸Ń
    0.09
     ë¶Ħìķ¼ìĿĺ
    0.09
    Activations Density 0.193%

    No Known Activations