© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    total number

    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
    ç²¾è¯ļ
    -0.07
    åĵī
    -0.07
    æĺ±
    -0.06
    ç¢
    -0.06
    æIJŃæ¡£
    -0.06
    é£İ顺
    -0.06
    æĹłåĬŁ
    -0.06
    éļıæīĭ
    -0.06
    æĪIJç«ĭæĹ¥æľŁ
    -0.06
    ä¼´
    -0.06
    POSITIVE LOGITS
    ä¸ĢåĽ¾
    0.08
    ebas
    0.08
    ä»ĸè·Ł
    0.08
    uds
    0.08
    å¸ļ
    0.07
    iever
    0.07
    ×ķ×ijר
    0.07
    åĨ²åĨ²
    0.07
    åħĦå¼Ł
    0.07
    sizei
    0.07
    Activations Density 0.006%

    No Known Activations