© 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. 11547
    Prev
    Next
    INDEX
    Explanations

    transcription, optical, transport, conduct

    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
    çļĦæŃ£
    -0.08
    å¹´è´§
    -0.08
    æĺ¥ç¬ĭ
    -0.08
    主è¦ģç»ıèIJ¥
    -0.08
     avanti
    -0.07
    á»Ļ
    -0.07
    å¾®åķĨ
    -0.07
     Forward
    -0.07
    æĹħ游度åģĩåĮº
    -0.07
    кала
    -0.07
    POSITIVE LOGITS
    åIJİèĩ³
    0.09
     ÑģобÑģÑĤвенно
    0.08
     transport
    0.08
     itself
    0.07
     Transport
    0.07
    çĤ¹èĩ³
    0.07
    æľĢåIJİä¸Ģåħ¬éĩĮ
    0.07
    çŃīçݯèĬĤ
    0.07
    æľ¬èº«
    0.07
    åIJĦçݯèĬĤ
    0.07
    Activations Density 0.165%

    No Known Activations