© 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. 16890
    Prev
    Next
    INDEX
    Explanations

    ethnic groups and professions

    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
    atten
    -0.06
    ")+
    -0.06
    alez
    -0.06
    丢
    -0.06
    åİĭåĢĴ
    -0.06
    OID
    -0.06
    èĩªä¸Ĭ
    -0.06
    objs
    -0.06
     radios
    -0.06
    åĺ¿
    -0.06
    POSITIVE LOGITS
    plex
    0.06
    纱
    0.05
    åĮªæµħ
    0.05
     intric
    0.05
    ibel
    0.05
    質
    0.05
     cycle
    0.05
    ume
    0.05
    äºĨä¸Ģ次
    0.05
    éĩįç£ħ
    0.05
    Activations Density 0.013%

    No Known Activations