© 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. 2012
    Prev
    Next
    INDEX
    Explanations

    sigma-algebra, stable, sub, relocation

    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
    ä¸ĩåĽ½
    -0.07
    ÅĻ
    -0.07
    æĽ´åģ¥åº·
    -0.07
    å±ĢçļĦ
    -0.07
    .deb
    -0.07
    ç¾İçijŀ
    -0.06
    å±ħå¤ļ
    -0.06
    èĬĤçļĦ
    -0.06
    å±Ģå±Ģéķ¿
    -0.06
    çļĦæľīæķĪ
    -0.06
    POSITIVE LOGITS
    elik
    0.08
    å¼ĢæĶ¾æĢ§
    0.07
    åĮħ容
    0.07
    çIJħ
    0.07
    稳å®ļæĢ§
    0.07
    æĢ§è¡Į为
    0.07
     vững
    0.07
    esso
    0.07
    é²ľ
    0.07
    æĢ§
    0.07
    Activations Density 0.006%

    No Known Activations