© 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. 56457
    Prev
    Next
    INDEX
    Explanations

    gender, sex, state, assignment

    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
    oura
    -0.08
    ominator
    -0.07
     ìłIJìĹIJìĦľ
    -0.07
    haj
    -0.07
    omme
    -0.07
    èݱæĸ¯
    -0.07
     omas
    -0.07
    umer
    -0.07
     gede
    -0.07
    大åĪ°
    -0.07
    POSITIVE LOGITS
    åıį转
    0.09
    å½Ĵå±ŀ
    0.08
     status
    0.08
     labels
    0.08
    /status
    0.08
    ä¼ĺåĬ£
    0.08
     switch
    0.08
    -switch
    0.07
     assignment
    0.07
     Status
    0.07
    Activations Density 0.104%

    No Known Activations