© 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. 16507
    Prev
    Next
    INDEX
    Explanations

    equations with variables

    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
    çªĿ
    -0.07
    è±Ĩçĵ£
    -0.07
    abad
    -0.07
    并åıij
    -0.07
    Ã¤ÃŁ
    -0.07
    YTE
    -0.07
    íľĺ
    -0.06
    éĻ·
    -0.06
    佬
    -0.06
    å¸ĥæĸ¯
    -0.06
    POSITIVE LOGITS
     fruition
    0.08
     Trinh
    0.08
    éħĿ
    0.07
    ogna
    0.07
    æ²³ä¸ľ
    0.07
    KeySpec
    0.07
    åĽ½åįİ
    0.07
    å¸ĮæľĽå¯¹
    0.07
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    0.07
    åĭĺ
    0.07
    Activations Density 0.080%

    No Known Activations