© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17258
    Prev
    Next
    INDEX
    Explanations

    biological sex and family groups

    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
    æīĵè¿Ľ
    -0.08
    eno
    -0.07
    ddl
    -0.07
    家人çļĦ
    -0.07
    VAR
    -0.07
    åīįä¸īåIJį
    -0.07
    åŃ¦å¼Ł
    -0.07
    iskon
    -0.07
    ä¹ĸ
    -0.07
    lej
    -0.07
    POSITIVE LOGITS
    æĹ¢æĺ¯
    0.08
    ĻĤ
    0.08
     genotype
    0.07
     оÑģоби
    0.07
    è°ģçŁ¥éģĵ
    0.07
    åľ¨èģĮ
    0.07
    å°Ĩè¿ĻäºĽ
    0.07
    个ä½ĵ
    0.07
    åįģä¹Ŀå±Ĭ
    0.07
    apiro
    0.07
    Activations Density 0.007%

    No Known Activations