© 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. 22351
    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
    Not in Any Lists

    No Comments

    Negative Logits
    owi
    -0.06
    ä¸ľè¥¿
    -0.06
    ancock
    -0.06
     forthcoming
    -0.06
    chunk
    -0.06
    shadow
    -0.05
    æ»ļæ»ļ
    -0.05
    .spawn
    -0.05
    åĬłåĭĴ
    -0.05
    åĴĮé¼ĵåĬ±
    -0.05
    POSITIVE LOGITS
    ụy
    0.06
    é«ĺ
    0.05
     dep
    0.05
    aiss
    0.05
    è²ł
    0.05
     gener
    0.05
    oves
    0.05
    릴
    0.05
     ÑĢадÑĥ
    0.05
     negoci
    0.05
    Activations Density 0.000%

    No Known Activations