© 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. 46655
    Prev
    Next
    INDEX
    Explanations

    place names, banks, and public utilities

    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
    à¹Į
    -0.07
     similarly
    -0.06
    1
    -0.06
    åł´åIJĪ
    -0.06
    æѤ类
    -0.06
    ฯ
    -0.06
    ä¹İ
    -0.05
     interp
    -0.05
    åĪĩå®ŀæĬĬ
    -0.05
    该类
    -0.05
    POSITIVE LOGITS
     âĵĺ
    0.08
    ãĥªãĥ¼ãĤ¹
    0.08
    åĬłè½½æĽ´å¤ļ
    0.08
    prio
    0.08
    ÓĻÑĢ
    0.07
    HAS
    0.07
    é«ĺçŃīä¸ĵç§ijåŃ¦æł¡
    0.07
     enfin
    0.07
    äºĮåįģäºĶ
    0.07
    é¦ĸéĥ¨
    0.07
    Activations Density 0.069%

    No Known Activations