© 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. 47656
    Prev
    Next
    INDEX
    Explanations

    health and development goals

    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
    øb
    -0.09
    <|box_end|>
    -0.09
    kamer
    -0.09
    个人è¡Į为
    -0.08
     revan
    -0.08
    à¸łà¸´
    -0.08
    æݧåĪ¶å¥½
    -0.08
    ertest
    -0.08
     fria
    -0.08
     republik
    -0.08
    POSITIVE LOGITS
     UNESCO
    0.11
    åħ¨çIJĥ
    0.10
     ÐŀÐŀÐĿ
    0.09
     global
    0.09
    èģĶåIJĪåĽ½
    0.09
    çļĦåħ¨çIJĥ
    0.09
     UN
    0.09
     WHO
    0.09
     worldwide
    0.09
     poverty
    0.08
    Activations Density 0.187%

    No Known Activations