© 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. 45788
    Prev
    Next
    INDEX
    Explanations

    dogs, veterinary, owners

    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
     Women
    -0.08
     Frauen
    -0.08
    èĿī
    -0.07
    æ¼±
    -0.07
    วะ
    -0.07
    ç¥Ń
    -0.06
     bif
    -0.06
     quasi
    -0.06
    uding
    -0.06
    失æķĪ
    -0.06
    POSITIVE LOGITS
    主人çļĦ
    0.13
    主人
    0.13
     пиÑĤом
    0.12
     veterinary
    0.11
     owners
    0.11
     veterin
    0.11
    çīł
    0.11
     Veterinary
    0.11
     veterinarian
    0.11
    çļĦ主人
    0.10
    Activations Density 0.250%

    No Known Activations