© 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. 49141
    Prev
    Next
    INDEX
    Explanations

    prospective randomized study

    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
    æĪĸåĪ©çĶ¨
    -0.09
    æĪĸèĢħåħ¶ä»ĸ
    -0.09
    æĪĸåħ¶
    -0.09
    æĪĸæľįåĬ¡
    -0.09
    è¸ıè¸ıå®ŀ
    -0.08
    æĪĸå¤ļ个
    -0.08
    æĪĸåħ¶ä»ĸ
    -0.08
    èĪ¬åľ°
    -0.07
    æĪĸå°ı
    -0.07
    æĪĸå°ij
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.21
    ãģĭãģ¤
    0.16
    ä¸Ķæľī
    0.16
    ä¸Ķåħ·æľī
    0.16
    ä¸Ķä¸į
    0.15
    ä¸Ķåľ¨
    0.15
    ãĢģ
    0.13
    à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    0.13
    并ä¸Ķ
    0.12
    èĢĮä¸Ķæĺ¯
    0.12
    Activations Density 0.339%

    No Known Activations