© 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. 50029
    Prev
    Next
    INDEX
    Explanations

    '.

    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
    åıªåı¯æĥľ
    -0.11
    ä¸įä¸Ģå®ļæĺ¯
    -0.11
    ä¸įä¸Ģå®ļ
    -0.10
    æľªå¿ħ
    -0.09
    ãģłãģijãģ§ãģ¯
    -0.09
    åį´æ²¡æľī
    -0.08
    åį´ä¸įæĺ¯
    -0.08
    ä½Ĩä¸įæĺ¯
    -0.08
    éļħ
    -0.08
    ä¸įä¼ļåĨį
    -0.08
    POSITIVE LOGITS
     ÐĹаÑĤо
    0.15
    ä½Ĩåı¯ä»¥
    0.15
    ä½Ĩæľī
    0.13
     заÑĤо
    0.12
    代ãĤıãĤĬãģ«
    0.10
     nevertheless
    0.10
     Nonetheless
    0.10
     nonetheless
    0.09
     nor
    0.09
    èĢĮæĺ¯åľ¨
    0.09
    Activations Density 0.182%

    No Known Activations