© 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. 47407
    Prev
    Next
    INDEX
    Explanations

    geographical regions and types

    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
    iones
    -0.06
    al
    -0.06
    çIJ³
    -0.06
    æľĭ
    -0.06
    ions
    -0.06
    å¾·æĸ¯
    -0.05
    —a
    -0.05
    æĿ¥åIJ§
    -0.05
    æ¡ħ
    -0.05
    ip
    -0.05
    POSITIVE LOGITS
    ãģĿãģĹãģ¦
    0.12
     ê·¸ë¦¬ê³ł
    0.11
     à¹ģละ
    0.10
     ฯลฯ
    0.10
    è¿Ļ两ç§į
    0.09
     ãģĿãģĹãģ¦
    0.09
    ,and
    0.09
     etc
    0.09
     à¹ģละà¸ģาร
    0.09
    以åıĬ
    0.09
    Activations Density 0.270%

    No Known Activations