© 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. 45751
    Prev
    Next
    INDEX
    Explanations

    debugging

    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
    ä¸ĢæĦı
    -0.09
     semula
    -0.08
    ErrMsg
    -0.08
    ByteBuffer
    -0.08
    culator
    -0.08
    åĽŀäºĭ
    -0.08
    /Page
    -0.08
    ä¸Ģåĭº
    -0.08
    elsen
    -0.07
    ventus
    -0.07
    POSITIVE LOGITS
    ging
    0.10
    GING
    0.09
    bing
    0.08
    ing
    0.08
    ราà¸Ĭà¸ģาร
    0.08
    licherweise
    0.07
    zac
    0.07
    gers
    0.07
    itta
    0.07
    گاÙĩ
    0.07
    Activations Density 0.060%

    No Known Activations