© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22562
    Prev
    Next
    INDEX
    Explanations

    full of

    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
    Negative Logits
    åĮĸçļĦ
    -0.07
    åĮĸåĴĮ
    -0.07
    ëį°
    -0.07
    ми
    -0.07
    åĮĸäºĨ
    -0.06
    Ùĩ
    -0.06
    en
    -0.06
    æĤ£å¤Ħ
    -0.06
    ãģĺãĤģãģ¦
    -0.06
    æ¯ĶçļĦ
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    ness
    0.07
    ij¸
    0.06
    è¦ģæł¹æį®
    0.05
    eds
    0.05
    nger
    0.05
    æł·
    0.05
     /\
    0.05
    溢
    0.05
    à¸Ńà¸ĩ
    0.05
    Activations Density 0.003%

    No Known Activations