© 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. 19299
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Sav
    -0.05
    ØŃد
    -0.05
    MT
    -0.05
    çļĦåIJį
    -0.05
    復活
    -0.05
    æŃ£å¦Ĥ
    -0.05
    羣æŃ£å®ŀçİ°
    -0.05
    еÑħа
    -0.05
    çĶµèĦijçīĪ
    -0.05
    åĽłäºº
    -0.05
    POSITIVE LOGITS
     emer
    0.06
    åĨįçĤ¹åĩ»
    0.06
    alang
    0.06
    iola
    0.06
     (*(
    0.06
    ä¸įè¿Ľ
    0.06
    éĿ¢å¯¹éĿ¢
    0.06
    举æŃ¢
    0.06
    ãĤ¶ãĥ¼
    0.06
     bul
    0.06
    Activations Density 0.000%

    No Known Activations