© 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. 48333
    Prev
    Next
    INDEX
    Explanations

    examples or eg

    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
    åħįè´¹åĴ¨è¯¢
    -0.08
    ä¿Ŀ驾
    -0.08
    çŁ¥åħ¶
    -0.08
    amac
    -0.07
    _blocking
    -0.07
    lat
    -0.07
    nect
    -0.07
    æĴŃ
    -0.07
     JetBrains
    -0.07
    åĢ¼å¾Ĺä¹°
    -0.07
    POSITIVE LOGITS
     example
    0.12
    示ä¾ĭ
    0.11
    èĮĥä¾ĭ
    0.11
    ä¾ĭåŃIJ
    0.11
     examples
    0.10
    ä¾ĭ
    0.10
    /example
    0.10
    çļĦä¾ĭåŃIJ
    0.10
    _example
    0.10
    example
    0.09
    Activations Density 0.067%

    No Known Activations