© 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. 63301
    Prev
    Next
    INDEX
    Explanations

    male, helper, adult, linux, dependent

    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
    大好
    -0.07
    iedz
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.07
    einander
    -0.07
    å°ıäºĮ
    -0.07
    åĴĮçĪ±
    -0.06
    achel
    -0.06
    Import
    -0.06
    åĪĻæĺ¯
    -0.06
    еÑĢж
    -0.06
    POSITIVE LOGITS
    ä¹Łèĥ½
    0.11
    çŃīéĿŀ
    0.10
     sekalipun
    0.10
    å±ħçĦ¶
    0.09
    ä¹Łä¼ļæľī
    0.09
     ostensibly
    0.09
    è°ģ说
    0.08
    ç½ķè§ģçļĦ
    0.08
    ä»įåı¯
    0.08
    çħ§æł·
    0.08
    Activations Density 0.556%

    No Known Activations