© 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. 14131
    Prev
    Next
    INDEX
    Explanations

    triangle shape

    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
    èĬ¸
    -0.07
     aboard
    -0.07
    èĴ¸
    -0.07
    æ³¥
    -0.06
    ä¸įæ±Ĥ
    -0.06
    erso
    -0.06
    çļĦå¾®
    -0.06
    tiger
    -0.06
    åĴĮèĩªå·±çļĦ
    -0.06
    auer
    -0.06
    POSITIVE LOGITS
     triangular
    0.11
    ä¸īè§Ĵå½¢
    0.10
     triangle
    0.10
     triangles
    0.10
    ä¸īè§Ĵå½¢çļĦ
    0.10
    tri
    0.09
    å°ĸ
    0.09
    å°ĸ端
    0.09
    å°ĸéĶIJ
    0.09
     ÑĤÑĢеÑĥго
    0.09
    Activations Density 0.022%

    No Known Activations