© 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. 58423
    Prev
    Next
    INDEX
    Explanations

    CWE

    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
    ر
    -0.07
    icus
    -0.07
    辨è¯Ĩ
    -0.07
    ôr
    -0.06
    ä¸įè¯Ĩ
    -0.06
    atham
    -0.06
    æľīæĹł
    -0.06
    chants
    -0.06
     ]]
    -0.06
    ica
    -0.06
    POSITIVE LOGITS
    inee
    0.08
    åį«çĶŁç»Ħç»ĩ
    0.08
    ä»ĺ
    0.07
     prostitu
    0.07
    åĴĮ人æ°ij
    0.07
    æĺ¯éĿŀ
    0.07
     ÑĩеÑĢно
    0.07
    è¦ģæıIJé«ĺ
    0.07
    å¼łåĽ½
    0.07
    lina
    0.07
    Activations Density 0.001%

    No Known Activations