© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24760
    Prev
    Next
    INDEX
    Explanations

    ORDER / regulated / employment / danger

    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
    iches
    -0.08
    åİŁåĪĽæĸĩç«ł
    -0.08
    rze
    -0.08
    严äºİ
    -0.08
     moot
    -0.07
    éĶIJæĦıè¿Ľåıĸ
    -0.07
    æĹħ游度åģĩåĮº
    -0.07
    建çŃijè£ħ饰
    -0.07
    æĸ¹æ¡ĪåĴĮ
    -0.07
    اÙģت
    -0.07
    POSITIVE LOGITS
    æľī以ä¸ĭ
    0.07
    ardi
    0.07
    æľīä¸ĭåĪĹ
    0.07
    ثة
    0.07
    ä¸ĩ
    0.07
    以ä¸ĭåĩłçĤ¹
    0.07
     '
    0.06
    é©
    0.06
    yv
    0.06
    çģŃ
    0.06
    Activations Density 0.101%

    No Known Activations