© 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. 48944
    Prev
    Next
    INDEX
    Explanations

    adjacent, neighbor, consecutive

    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
    åįĩåĪĿ
    -0.08
    æķ£åİ»
    -0.08
    综åIJĪåĪĨæŀIJ
    -0.07
    ä¸įä¸ĭ
    -0.07
    gba
    -0.07
    空éĹ´åĴĮ
    -0.07
    åı¬
    -0.06
     userInfo
    -0.06
    许æĦ¿
    -0.06
    yasi
    -0.06
    POSITIVE LOGITS
    缸éĤ»
    0.13
    éĵ¾
    0.11
     adjacent
    0.11
    éĵ¾æĿ¡
    0.11
     chain
    0.10
    éĤ»
    0.10
     chains
    0.10
     Chain
    0.10
    Adjacent
    0.09
    éļ£
    0.09
    Activations Density 0.017%

    No Known Activations