© 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. 39257
    Prev
    Next
    INDEX
    Explanations

    personal information and privacy

    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
    æīĭæľºéĺħ读
    -0.07
     precon
    -0.07
    ФÐŀ
    -0.06
     dess
    -0.06
    å¸Ĥåľºå¯¹
    -0.06
    å°±ä½į
    -0.06
    社ä¼ļæķĪçĽĬ
    -0.06
    åı¥åı¥
    -0.06
     bureaucracy
    -0.06
     whichever
    -0.06
    POSITIVE LOGITS
    éļIJç§ģ
    0.11
     stored
    0.10
    stored
    0.09
     privacy
    0.09
    Privacy
    0.09
    èĦĨå¼±
    0.09
    个人éļIJç§ģ
    0.09
     Stored
    0.09
     vulner
    0.08
     vulnerable
    0.08
    Activations Density 0.116%

    No Known Activations