© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21171
    Prev
    Next
    INDEX
    Explanations

    geographical names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iele
    -0.06
    à¸Ľà¸±à¹īà¸Ļ
    -0.06
    è£ģå®ļ书
    -0.06
    irin
    -0.05
    å®īè£ħè°ĥè¯ķ
    -0.05
    è¿ĶåĽŀåĪĹ表
    -0.05
     therein
    -0.05
    antung
    -0.05
    缺ä¸Ģä¸įåı¯
    -0.05
     سÙĪØ¡
    -0.05
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.06
    ways
    0.05
     even
    0.05
    çĶļèĩ³
    0.05
     tor
    0.05
    以èĩ³
    0.05
    çĶļèĩ³æľīäºĽ
    0.05
    ucks
    0.05
    饮水
    0.05
     Tor
    0.05
    Activations Density 0.037%

    No Known Activations