© 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. 17635
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    å¦Ĥæŀľèĥ½å¤Ł
    -0.08
    å¦Ĥæŀľèĥ½
    -0.07
    èĭ¥èĥ½
    -0.07
    ables
    -0.07
    Enough
    -0.07
    ifax
    -0.07
    ä¸įå°ij
    -0.07
    好åIJĹ
    -0.07
    деб
    -0.06
    ToArray
    -0.06
    POSITIVE LOGITS
    isku
    0.08
    èµ·è§ģ
    0.08
    ее
    0.08
    uyu
    0.08
    aspers
    0.08
    çľģäºĭ
    0.07
    æĿ¡
    0.07
    ä»İ头
    0.07
    羣æĥ³
    0.07
    зе
    0.07
    Activations Density 0.155%

    No Known Activations