© 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. 61575
    Prev
    Next
    INDEX
    Explanations

    maximize the law

    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
     whichever
    -0.07
    å°ıé¢Ŀ
    -0.07
     reportedly
    -0.07
    ennon
    -0.07
    edula
    -0.06
     Citizen
    -0.06
    éĿĻéĿĻçļĦ
    -0.06
     rile
    -0.06
    å·Ŀ
    -0.06
     bastante
    -0.06
    POSITIVE LOGITS
    ä¸įåıĬæŶ
    0.09
    ä¸įåºĶ
    0.09
    éģ½
    0.09
    ä¸įåºĶ该
    0.08
     somehow
    0.08
     непÑĢеменно
    0.08
    aku
    0.08
    éĶĻ误æĪĸ
    0.08
    éĥ½ä¸įåı¯èĥ½
    0.08
    è¿ĩå¤ļ
    0.08
    Activations Density 0.092%

    No Known Activations