© 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. 64303
    Prev
    Next
    INDEX
    Explanations

    life expectancy

    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
    leon
    -0.08
     discrete
    -0.07
    檸
    -0.07
    )._
    -0.06
    æĻ¨æĬ¥
    -0.06
     (++
    -0.06
    FC
    -0.06
    说çļĦè¯Ŀ
    -0.06
     ëĩ
    -0.06
    athed
    -0.06
    POSITIVE LOGITS
    åĪĩå®ŀåģļåĪ°
    0.08
    à¹Īาว
    0.07
    óm
    0.07
    è¦ģåģļåĪ°
    0.07
    åı¯ä»İ
    0.07
    è§ĦåĪĴ设计
    0.07
    æľīåĵªäºĽåij¢
    0.07
    åģļåĪ°
    0.06
    onne
    0.06
    ä¸į缺
    0.06
    Activations Density 0.029%

    No Known Activations