© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    spokeswoman said

    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
    ker
    -0.08
    ika
    -0.08
    rau
    -0.07
    infer
    -0.07
    å©ķ
    -0.06
    uxt
    -0.06
    ifer
    -0.06
    å¾Ĺ好
    -0.06
     unfortunate
    -0.06
     ourselves
    -0.06
    POSITIVE LOGITS
    ä»ĸ说
    0.09
    æį®ä»ĭç»į
    0.09
     spokeswoman
    0.08
    æį®
    0.08
    ä»ĸ說
    0.08
     :=
    0.08
    她说
    0.08
    åľ¨æѤä¹ĭåīį
    0.08
    ä»ĸ表示
    0.08
     prelim
    0.07
    Activations Density 1.701%

    No Known Activations