© 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. 7446
    Prev
    Next
    INDEX
    Explanations

    a/an/two followed by noun

    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
    æss
    -0.08
    丽èIJį
    -0.07
     EINVAL
    -0.07
     سÙħÙĪ
    -0.07
    è¿ĩ好
    -0.07
    agerie
    -0.07
    产åĵģç»ĵæŀĦ
    -0.07
    borough
    -0.07
    ÑģиÑİ
    -0.07
    иÑĤоÑĢ
    -0.07
    POSITIVE LOGITS
    åIJĮä¸Ĭ
    0.07
    ille
    0.07
     valued
    0.07
    åijĺ
    0.06
    -val
    0.06
    åIJ¯
    0.06
    val
    0.06
     Ware
    0.06
    æľª
    0.06
    ä»ħæľīçļĦ
    0.06
    Activations Density 0.049%

    No Known Activations