© 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. 28182
    Prev
    Next
    INDEX
    Explanations

    additional, contributes, extra, added

    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
    çݩ转
    -0.09
    æīĢå¤ĦçļĦ
    -0.08
    ä»»ä½ķä¸Ģ个
    -0.08
     gäng
    -0.08
    æľīä»»ä½ķ
    -0.08
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    亲们
    -0.07
     demás
    -0.07
    æĪijçļĦè¯Ŀ
    -0.07
    Pretty
    -0.07
    POSITIVE LOGITS
    é¢Ŀå¤ĸçļĦ
    0.14
     additional
    0.13
    é¢Ŀå¤ĸ
    0.12
    additional
    0.11
    Additional
    0.09
     дополниÑĤелÑĮнÑĭй
    0.09
     Additional
    0.09
     extra
    0.09
    éĻĦåĬł
    0.09
    é¡įå¤ĸ
    0.09
    Activations Density 0.037%

    No Known Activations