© 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. 50547
    Prev
    Next
    INDEX
    Explanations

    commercial products and features

    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
    åłĤ
    -0.07
    ä¼ı
    -0.07
    æī§
    -0.06
    è¢Ĵ
    -0.06
     deliberate
    -0.06
    alley
    -0.06
    交代
    -0.06
    aseline
    -0.06
    å¦ĵ
    -0.06
    bu
    -0.06
    POSITIVE LOGITS
     marketed
    0.11
     advertised
    0.10
    å¸ĤéĿ¢ä¸Ĭ
    0.09
     Anbieter
    0.09
    类产åĵģ
    0.09
     designed
    0.09
     Designed
    0.08
    å¸ĤéĿ¢ä¸ĬçļĦ
    0.08
    产åĵģ设计
    0.08
    宣称
    0.08
    Activations Density 0.316%

    No Known Activations