© 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. 22438
    Prev
    Next
    INDEX
    Explanations

    understand what's going on

    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
    utti
    -0.07
    inia
    -0.06
    åıĤèĢĥ
    -0.06
     ÙĨت
    -0.06
    ane
    -0.05
    /pm
    -0.05
    设å®ļçļĦ
    -0.05
    ấn
    -0.05
     Interpreter
    -0.05
    åijĬ
    -0.05
    POSITIVE LOGITS
    åį³ä½¿åľ¨
    0.07
    åį³ä½¿
    0.07
     even
    0.07
    åį³ä¾¿æĺ¯
    0.06
    åį³ä½¿æĺ¯
    0.06
    åį³ä¾¿
    0.06
     Even
    0.06
    åĽĽåij¨
    0.06
    even
    0.06
     still
    0.06
    Activations Density 0.001%

    No Known Activations