© 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. 17818
    Prev
    Next
    INDEX
    Explanations

    comprehension and knowledge acquisition

    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
    egin
    -0.08
    çİĦæѦ
    -0.07
    ovol
    -0.07
    ourn
    -0.07
    ä½ľä¸ºåĽ½åĨħ
    -0.07
    iov
    -0.07
    antau
    -0.07
    åIJĵ
    -0.07
    èĦIJ
    -0.07
    arina
    -0.07
    POSITIVE LOGITS
    çŁ¥è¯ĨçļĦ
    0.10
    æĸ°çŁ¥è¯Ĩ
    0.10
    åIJ¬è®²
    0.10
    æŁ¥æ¼ı补缺
    0.10
     comprehension
    0.10
    举ä¸Ģåıįä¸ī
    0.09
    补缺
    0.09
    çŁ¥è¯ĨçĤ¹
    0.09
    Chunk
    0.09
    é¢Ħä¹ł
    0.08
    Activations Density 0.026%

    No Known Activations