© 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. 22184
    Prev
    Next
    INDEX
    Explanations

    fecal matter

    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
    ®
    -0.06
    æĶ¶
    -0.05
     pura
    -0.05
    orks
    -0.05
    åIJĮåŁİ
    -0.05
    ä¹ĸ
    -0.05
    å½¼
    -0.05
    á»Ŀ
    -0.05
    resse
    -0.05
    ä¸ĵéŨ
    -0.05
    POSITIVE LOGITS
    æ´Ĵ
    0.06
    ä¸įå®ļ
    0.05
    æĪijä¹Łä¸įçŁ¥éģĵ
    0.05
    ürg
    0.05
    emic
    0.05
    alam
    0.05
    .Download
    0.05
    èIJ½åĪ°
    0.05
    èĢĮçŁ¥
    0.05
    falls
    0.05
    Activations Density 0.003%

    No Known Activations