© 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. 22609
    Prev
    Next
    INDEX
    Explanations

    represent database tables

    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
    QC
    -0.07
    meni
    -0.06
     pan
    -0.06
    عب
    -0.06
     thÆ°Æ¡ng
    -0.06
    aderas
    -0.06
    åı¯è§Ĩ
    -0.06
     rep
    -0.06
    erlo
    -0.05
     Ø´Ùĥ
    -0.05
    POSITIVE LOGITS
     economy
    0.05
    anth
    0.05
    ustin
    0.05
     Economy
    0.05
    ander
    0.05
    /includes
    0.05
    ensee
    0.05
    primary
    0.05
    éĩ
    0.05
    min
    0.05
    Activations Density 0.028%

    No Known Activations