© 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. 16998
    Prev
    Next
    INDEX
    Explanations

    body and bodily experiences

    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
    ä¸įäºĨ
    -0.06
    æķ´ä¸ªéĹ®é¢ĺ
    -0.06
    olec
    -0.06
     évent
    -0.05
    iding
    -0.05
    ë¥ĺ
    -0.05
    allas
    -0.05
    iza
    -0.05
    ç»Ŀ大éĥ¨åĪĨ
    -0.05
    å¾Īå¤ļéĹ®é¢ĺ
    -0.05
    POSITIVE LOGITS
    人人
    0.06
     seber
    0.06
    oplast
    0.05
    omatis
    0.05
    åħĥèĩ³
    0.05
    antino
    0.05
     Rede
    0.05
    æĢªåħ½
    0.05
    egah
    0.05
    人æ°ijæ³ķéĻ¢
    0.05
    Activations Density 0.002%

    No Known Activations