© 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. 16638
    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
    对æĪijçļĦ
    -0.06
    ez
    -0.06
    à¤Ĥध
    -0.06
    aub
    -0.06
    наÑĩ
    -0.06
    åĽ½ç±į
    -0.06
    aux
    -0.05
     matrim
    -0.05
    din
    -0.05
    acias
    -0.05
    POSITIVE LOGITS
    tienen
    0.06
    ør
    0.05
    /etc
    0.05
    ets
    0.05
    ä¾Ľå¥ī
    0.05
    èĨĬ
    0.05
     kidd
    0.05
    ÑĢное
    0.05
    lore
    0.05
     zero
    0.04
    Activations Density 0.000%

    No Known Activations