© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17555
    Prev
    Next
    INDEX
    Explanations

    phrases, statements, direction

    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
    igno
    -0.09
    该项
    -0.08
    ono
    -0.08
    ients
    -0.08
    ajukan
    -0.07
    æ¹ĸçķĶ
    -0.07
    ê·
    -0.07
    unk
    -0.07
    orno
    -0.07
    łĢ
    -0.07
    POSITIVE LOGITS
    èĩ
    0.08
    æľīèĩ´
    0.07
    eny
    0.07
    èĮ¨
    0.07
    åı¦å¤ĸä¸Ģç§į
    0.07
    eldet
    0.07
    以身
    0.06
    åı¦ä¸Ģç§į
    0.06
    ä¸į欲
    0.06
    å²IJ
    0.06
    Activations Density 0.001%

    No Known Activations