© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20734
    Prev
    Next
    INDEX
    Explanations

    Grand Theft Auto V

    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
    aint
    -0.06
    æIJľç´¢èµĦæĸĻ
    -0.06
    inus
    -0.05
    pell
    -0.05
    à¸Ļà¹īà¸Ńย
    -0.05
    obel
    -0.05
     Ferm
    -0.05
    åıĤä¼ļ人åijĺ
    -0.05
    è¿ĩæ²³
    -0.05
    ä¸ĵåĪ©ä¿¡æģ¯
    -0.05
    POSITIVE LOGITS
    é£Ļ
    0.06
    ç»Ī身
    0.06
    isian
    0.06
     Verst
    0.05
    éĢįéģ¥
    0.05
    orden
    0.05
    ÃĤN
    0.05
    ãĥŀãĥĭãĥ¥ãĤ¢ãĥ«
    0.05
     ì²´
    0.05
     sân
    0.05
    Activations Density 0.003%

    No Known Activations