© 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. 16692
    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
    edly
    -0.06
    shal
    -0.06
    biology
    -0.06
    holds
    -0.06
    zd
    -0.06
    ially
    -0.06
     Coll
    -0.06
    ionalmente
    -0.06
    ]*)
    -0.06
    artig
    -0.06
    POSITIVE LOGITS
    åĮĸ
    0.06
    ä¼Ĺ
    0.06
    س
    0.05
    å¸Ĩ
    0.05
    缼
    0.05
     Owners
    0.05
    æł¼å°Ķ
    0.05
    æį·
    0.05
     approaches
    0.05
    encing
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.