© 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. 50818
    Prev
    Next
    INDEX
    Explanations

    one seems

    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
    该åĨħ容
    -0.07
    è¿Ļç§įåģļæ³ķ
    -0.07
    è¿Ļéĥ¨åĪĨ
    -0.07
    è¿Ļç§įçݰ象
    -0.06
    è¿Ļç§įæĥħåĨµ
    -0.06
    è¿Ļé¡¹å·¥ä½ľ
    -0.06
    éĤ£éĩĮçļĦ
    -0.06
    åĨ¥
    -0.06
    çıł
    -0.06
    çļĦå·¥ä½ľä¸Ń
    -0.06
    POSITIVE LOGITS
    roda
    0.08
    alink
    0.08
    eprom
    0.08
    licer
    0.08
    çij¾
    0.08
    iland
    0.08
    olta
    0.08
    ä»ĸãģ«ãĤĤ
    0.07
    ä¸įåİ»
    0.07
    opo
    0.07
    Activations Density 0.598%

    No Known Activations