© 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. 17243
    Prev
    Next
    INDEX
    Explanations

    gaming and playing video games

    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
    wap
    -0.06
    oi
    -0.06
    oy
    -0.05
    Ø·Ùħ
    -0.05
    ÑĢаÑī
    -0.05
    ussen
    -0.05
    å¼ı设计
    -0.05
    netinet
    -0.05
    ple
    -0.05
    èµ·
    -0.05
    POSITIVE LOGITS
    æĦŁæĤŁ
    0.06
    主è¦ģçĶ¨äºİ
    0.06
    éģĹ迹
    0.06
    alted
    0.05
    event
    0.05
    tops
    0.05
     staged
    0.05
    -event
    0.05
    åįģäºĮç«ł
    0.05
    textAlign
    0.05
    Activations Density 0.006%

    No Known Activations