© 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. 4113
    Prev
    Next
    INDEX
    Explanations

    code, link, transcript, logic

    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
    ionato
    -0.07
    -led
    -0.07
    æĹłä¸Ĭ
    -0.06
    æľīè¯Ŀ
    -0.06
    ¢
    -0.06
    aData
    -0.06
    æݲ示æĿ¿
    -0.06
    rio
    -0.06
    åı£ä¸ŃçļĦ
    -0.06
    taja
    -0.06
    POSITIVE LOGITS
     exact
    0.09
     approximate
    0.08
     necessary
    0.08
    åħ·ä½ĵ
    0.08
    åħ·ä½ĵçļĦãģª
    0.08
     details
    0.08
    å®Įæķ´çļĦ
    0.08
    åĪĨ享ç»Ļ大家
    0.07
     recommended
    0.07
    ecessary
    0.07
    Activations Density 0.108%

    No Known Activations