© 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. 64231
    Prev
    Next
    INDEX
    Explanations

    no, stand, ground, guns, lines

    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
    mot
    -0.07
    åıijæĦģ
    -0.07
    俯
    -0.07
    èĢģå°ij
    -0.06
    åĩij
    -0.06
    æīĭå¿Ļ
    -0.06
    忧
    -0.06
    มà¸Ļ
    -0.06
    ä¸įåıĬ
    -0.06
     mò
    -0.06
    POSITIVE LOGITS
    æįįåį«
    0.15
    Assert
    0.13
     assert
    0.13
    åĿļå®ļçļĦ
    0.13
    ç«ĭåľº
    0.13
    åĿļå®ļ
    0.12
    assert
    0.12
     Assert
    0.12
    æĭĴç»Ŀ
    0.12
     assertion
    0.12
    Activations Density 0.156%

    No Known Activations