© 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. 56603
    Prev
    Next
    INDEX
    Explanations

    female gender and 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
    个人æĪĸ
    -0.08
    å¿«éĢŁèİ·åıĸ
    -0.08
    bacher
    -0.07
    valo
    -0.07
    鼶è·Ŀ离
    -0.07
    le
    -0.07
    char
    -0.07
    nock
    -0.06
    ologies
    -0.06
    erse
    -0.06
    POSITIVE LOGITS
    INTERNAL
    0.08
    inox
    0.08
     outnumber
    0.08
    à¤ķà¥įà¤Ł
    0.07
    tabil
    0.07
    ä¹Łä¼ļåĩºçİ°
    0.07
    ç¼
    0.07
    ablish
    0.07
     pÅĤ
    0.07
    åĨħ线
    0.07
    Activations Density 0.006%

    No Known Activations