© 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. 41181
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
    attel
    -0.06
    è°±
    -0.06
    ulon
    -0.06
    çļĦ巨大
    -0.06
    ader
    -0.06
    åİĭåĢĴ
    -0.06
    à¦ļার
    -0.06
    碾åİĭ
    -0.06
    atta
    -0.06
     overwhelmingly
    -0.06
    POSITIVE LOGITS
    çĤ¹å¤´
    0.08
    _VARIABLE
    0.08
    æĭĺå½¹
    0.07
    tó
    0.07
     Sungai
    0.07
    管æķĻ
    0.07
    çİīæłij
    0.07
    ossi
    0.07
    çĽĺé¾Ļ
    0.07
    ł
    0.07
    Activations Density 0.030%

    No Known Activations