© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46394
    Prev
    Next
    INDEX
    Explanations

    term, surface, geek

    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
    åĽłä¸ºæ²¡æľī
    -0.08
    鸦
    -0.08
     ìŀĪëĬĶëį°
    -0.07
    ä¹ĭæīĢ以
    -0.07
    讳
    -0.07
    è®°
    -0.07
    UED
    -0.07
     ìŀĪëĬĶëį°ìļĶ
    -0.07
    åĽłä¸ºä»ĸ
    -0.07
    uas
    -0.07
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.13
    ç¼ĺæķħ
    0.11
    èĢĮä¸Ķæľī
    0.09
    èĢĮä¸Ķ
    0.09
    èĢĮè¦ģ
    0.09
    åĺĽ
    0.08
    à¹Ħà¸ĩ
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    chow
    0.08
     whereas
    0.08
    Activations Density 0.155%

    No Known Activations