© 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. 60416
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    纵çĦ¶
    -0.08
    rong
    -0.08
    主é¢ĺæĺ¯
    -0.07
    lici
    -0.07
    ä½ľèĢħåľ¨
    -0.07
    æł©æł©
    -0.07
    åµĺ
    -0.06
    ãĤīãģĦ
    -0.06
    nic
    -0.06
    )>>
    -0.06
    POSITIVE LOGITS
    _fixture
    0.08
    attare
    0.07
    toMatchSnapshot
    0.07
    è§Ĩé¢ijçļĦ
    0.07
    etek
    0.07
    zków
    0.07
    ä¸ĢåĪ°
    0.06
     ...,
    0.06
    Ĩ
    0.06
     ?,
    0.06
    Activations Density 0.007%

    No Known Activations