© 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. 45824
    Prev
    Next
    INDEX
    Explanations

    gendered personal roles

    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
     Poor
    -0.07
    iglia
    -0.07
    æĺ¾
    -0.07
     persons
    -0.06
    Persons
    -0.06
     poor
    -0.06
     ill
    -0.06
    æĤ²æĥ¨
    -0.06
    æĪĸåĽł
    -0.06
    persons
    -0.06
    POSITIVE LOGITS
    æĬĬå·¥ä½ľ
    0.10
    对æĪijæĿ¥è¯´
    0.08
    éķ¿éĿĴ
    0.08
    èĥ½å¤Łè®©
    0.08
    iket
    0.08
    immers
    0.08
    æīĵè¿Ľ
    0.08
    DX
    0.08
    æīĢåģļ
    0.08
     wasn
    0.08
    Activations Density 0.117%

    No Known Activations