© 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. 62259
    Prev
    Next
    INDEX
    Explanations

    energy consumption and efficiency

    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
    -kit
    -0.08
    翼翼
    -0.08
    ë°©ì§Ģ
    -0.08
     ÑĢазвеÑĢ
    -0.08
    ÏĦοÏĢοι
    -0.07
    èįŁ
    -0.07
    amat
    -0.07
    纷åijĪ
    -0.07
     earliest
    -0.07
    对ä¸Ń
    -0.07
    POSITIVE LOGITS
    èĢĹ
    0.11
    æ¶ĪèĢĹçļĦ
    0.10
    èĥ½èĢĹ
    0.10
    èĬĤèĥ½
    0.10
     efficiency
    0.10
    大æĪ·
    0.09
     kWh
    0.09
     consumption
    0.09
    èĥ½æºIJ
    0.09
    çľģçĶµ
    0.09
    Activations Density 0.075%

    No Known Activations