© 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. 22347
    Prev
    Next
    INDEX
    Explanations

    .html or /

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ós
    -0.06
    ides
    -0.06
    гового
    -0.06
    ç½®
    -0.06
    οÏħ
    -0.06
    娥
    -0.05
    æıIJæIJº
    -0.05
    s
    -0.05
    urende
    -0.05
    表éĿ¢
    -0.05
    POSITIVE LOGITS
    ÙĦÙĦ
    0.06
    yal
    0.06
    èıģ
    0.06
    ìĭľê¸¸
    0.05
    ÑģÑĤеÑģÑĤвенно
    0.05
    åįģæľĪ
    0.05
     Cluster
    0.05
     dummy
    0.05
    é«ĺæ¡£
    0.05
     relev
    0.05
    Activations Density 0.024%

    No Known Activations