© 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. 57430
    Prev
    Next
    INDEX
    Explanations

    existing mainstream country neighbourhood

    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
    ede
    -0.07
     scenarios
    -0.06
    ếch
    -0.06
    áĢĨáĢŃáĢ¯
    -0.06
    è¾°
    -0.06
    忱
    -0.06
    _ve
    -0.06
    å¥
    -0.06
    ãĤĬè¿Ķ
    -0.06
    æĸ¥
    -0.06
    POSITIVE LOGITS
     existing
    0.11
    existing
    0.11
    æĹ¢åŃĺ
    0.10
    çİ°æľī
    0.10
    主æµģ
    0.10
     mainstream
    0.10
    (existing
    0.10
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.10
     Existing
    0.10
    çİ°æľīçļĦ
    0.10
    Activations Density 0.324%

    No Known Activations