© 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. 22617
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    инима
    -0.07
    taat
    -0.06
    ãy
    -0.06
    endszer
    -0.06
    ноÑģ
    -0.06
    inner
    -0.06
    repid
    -0.06
    -browser
    -0.06
    -inner
    -0.06
    ible
    -0.06
    POSITIVE LOGITS
    æĤī
    0.05
    kina
    0.05
    wach
    0.05
    ูà¹Ī
    0.05
    大åı¯
    0.05
     мака
    0.05
    getattr
    0.05
    大ä¸Ń
    0.05
    placed
    0.05
     Papua
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.