© 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. 22370
    Prev
    Next
    INDEX
    Explanations

    reporting sensitive information

    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
    论è¯ģ
    -0.07
    æĹ¶èµ·
    -0.07
    æķ£
    -0.07
    entin
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    ç¾ģ
    -0.07
    ismet
    -0.06
     Scatter
    -0.06
     scatter
    -0.06
    _argument
    -0.06
    POSITIVE LOGITS
    çķħæīĢ欲è¨Ģ
    0.12
     confidential
    0.11
    åĿ¦è¯ļ
    0.10
     cợi
    0.10
     openly
    0.10
    /report
    0.10
    èĥ½åıĬæŶ
    0.10
     anonim
    0.10
     reporting
    0.10
    çļĦåĭĩæ°Ķ
    0.10
    Activations Density 0.111%

    No Known Activations