© 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. 16734
    Prev
    Next
    INDEX
    Explanations

    visit our [marketing page](https://azure.microsoft.com/en-us/services/service-bus/). To learn more about our

    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
    æŶéĹ´æĿ¥
    -0.06
    rush
    -0.06
    Ø·Ùħ
    -0.06
    afür
    -0.06
    ¢
    -0.06
     незам
    -0.06
    æĸ¹æ³ķæĿ¥
    -0.06
     tonn
    -0.06
    åīįåIJİ
    -0.06
    akens
    -0.06
    POSITIVE LOGITS
    itle
    0.06
    ias
    0.05
    igu
    0.05
    iah
    0.05
    .");
    0.05
    bose
    0.05
    oba
    0.05
    л
    0.05
    æłĩçļĦçī©
    0.05
    ibat
    0.05
    Activations Density 0.062%

    No Known Activations