© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21203
    Prev
    Next
    INDEX
    Explanations

    olympic athletes

    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
    æĿ¾
    -0.05
     plac
    -0.05
    quet
    -0.05
    æĪij第ä¸Ģ次
    -0.05
     really
    -0.05
     da
    -0.05
     des
    -0.05
     gr
    -0.05
     de
    -0.05
    rit
    -0.05
    POSITIVE LOGITS
    .Mapping
    0.07
     estata
    0.07
    erman
    0.07
    ilé
    0.06
    terek
    0.06
     sacerdo
    0.06
    Allem
    0.06
    ellate
    0.06
    åIJĮæ¯Ķå¢ŀåĬł
    0.06
    fällig
    0.06
    Activations Density 0.003%

    No Known Activations