© 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. 16905
    Prev
    Next
    INDEX
    Explanations

    specific fields and roles

    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
    åIJĮæł·
    -0.07
     nemlig
    -0.06
     ë§Īì°¬ê°Ģì§Ģë¡ľ
    -0.06
    OrUpdate
    -0.06
    ä¸įä»ħ
    -0.06
    yal
    -0.06
    è¿Ŀåıįä¸Ĭè¿°
    -0.06
    å®ĥä¸įä»ħ
    -0.06
    endorf
    -0.06
     ìŀĪëĬĶëį°
    -0.06
    POSITIVE LOGITS
     etc
    0.12
     ฯลฯ
    0.12
    æ´»åĬ¨çŃī
    0.11
    ,and
    0.11
    æĬĢæľ¯çŃī
    0.10
    ä¸Ńå¿ĥçŃī
    0.10
    çŃīçŃī
    0.10
    æĥħåĨµçŃī
    0.10
    ç³»ç»ŁçŃī
    0.10
    管çIJĨçŃī
    0.10
    Activations Density 0.604%

    No Known Activations