© 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. 29406
    Prev
    Next
    INDEX
    Explanations

    confirmed, replicated, subsequent, scientists

    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
    æĪijå°±è¦ģ
    -0.09
     hạng
    -0.08
    unge
    -0.08
    amic
    -0.08
    ä¸įæĪIJ
    -0.08
    åĨīåĨī
    -0.08
     Assault
    -0.07
    å¹Į
    -0.07
    ä¹į
    -0.07
     belli
    -0.07
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥å®ĮåĸĦ
    0.13
     refined
    0.12
    è¿Ľä¸ĢæŃ¥æĺİç¡®
    0.12
     later
    0.12
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.11
    è¿Ľä¸ĢæŃ¥æݨåĬ¨
    0.11
    è¿Ľä¸ĢæŃ¥æī©å¤§
    0.11
     further
    0.11
     subsequent
    0.11
    å®ĮåĸĦäºĨ
    0.10
    Activations Density 0.195%

    No Known Activations