© 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. 16762
    Prev
    Next
    INDEX
    Explanations

    /user/ or /content/ or /product/

    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
    åŁº
    -0.05
    ica
    -0.05
    ç¨ĭ
    -0.05
    igo
    -0.05
    毫
    -0.05
    ====
    -0.05
    ä¹ĭäºĮ
    -0.05
    ored
    -0.05
    ifting
    -0.05
     General
    -0.05
    POSITIVE LOGITS
    uha
    0.06
    檻
    0.06
    éĵ¶å±±
    0.06
    forcements
    0.06
    iovas
    0.06
     Chiar
    0.06
    umont
    0.06
    æĹ¥ä»¥
    0.06
    bury
    0.06
    ASY
    0.05
    Activations Density 0.069%

    No Known Activations