© 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. 16701
    Prev
    Next
    INDEX
    Explanations

    UC followed by university names

    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
    Negative Logits
    tvr
    -0.08
    åľ¨æŀĹ
    -0.07
    centage
    -0.07
    éļ·
    -0.07
    inky
    -0.07
    åľ¨çĻ½
    -0.07
    enic
    -0.06
    èĢIJåĬĽ
    -0.06
    íĽ¨
    -0.06
    ocomplete
    -0.06
    POSITIVE LOGITS
    ä¸ļ
    0.05
    ns
    0.05
    et
    0.05
    ese
    0.05
    è¿Ļ个
    0.05
    essen
    0.05
    åĽº
    0.05
    est
    0.05
    ers
    0.05
    st
    0.05
    Activations Density 0.003%

    No Known Activations