© 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. 43489
    Prev
    Next
    INDEX
    Explanations

    versus, comparison, gender, self

    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
     Late
    -0.07
    atica
    -0.07
    ä¸īéĥ¨
    -0.07
    oen
    -0.07
    ç³»çļĦ
    -0.07
    Late
    -0.07
    idu
    -0.07
    owie
    -0.07
    ä¼
    -0.07
    OfDay
    -0.06
    POSITIVE LOGITS
     Eaton
    0.08
     Vers
    0.08
    Æ°u
    0.07
    nent
    0.07
    à¸Ŀà¹Īาย
    0.07
     versus
    0.07
     VERS
    0.07
    aner
    0.07
    ÙĨاÙĨ
    0.07
    vers
    0.07
    Activations Density 0.074%

    No Known Activations