© 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. 18089
    Prev
    Next
    INDEX
    Explanations

    Arabic, German, Chinese, Japanese

    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
    æĪ²
    -0.06
    åıĪåı«
    -0.05
     lik
    -0.05
     rius
    -0.05
    æĪı
    -0.05
    cite
    -0.05
     mÃŃt
    -0.05
    æĶ¶æ²»
    -0.05
    via
    -0.05
    ][_
    -0.05
    POSITIVE LOGITS
     رع
    0.06
    acht
    0.06
    ä¸Ģå®ļè¦ģ
    0.06
    ä¸Ģå¿ĥ
    0.06
    تاÙħ
    0.06
    owl
    0.06
    kanz
    0.06
    æĺ¯å±ŀäºİ
    0.06
    éķ¿ä¹ħ
    0.06
     dub
    0.06
    Activations Density 0.005%

    No Known Activations