© 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. 22622
    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
    该åİ¿
    -0.06
    ixo
    -0.05
    pio
    -0.05
    oth
    -0.05
    atable
    -0.05
    ìłģìĿ¸
    -0.05
     major
    -0.05
    fillna
    -0.05
    ((__
    -0.05
    æĦŁåįģ足
    -0.05
    POSITIVE LOGITS
    erti
    0.06
    itters
    0.06
    er
    0.06
    etts
    0.06
     Eyes
    0.06
    èº
    0.06
    æij¸æij¸
    0.06
    olle
    0.06
    eye
    0.06
     ang
    0.06
    Activations Density 0.000%

    No Known Activations