© 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. 22447
    Prev
    Next
    INDEX
    Explanations

    geographic or administrative divisions

    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
     bal
    -0.06
     mo
    -0.05
     (
    -0.05
     -
    -0.05
    æ¡£
    -0.05
     for
    -0.05
     a
    -0.05
     do
    -0.05
     alo
    -0.05
    ä¸ĥä¸ĥ
    -0.05
    POSITIVE LOGITS
    rest
    0.06
    -league
    0.06
     validations
    0.06
    ensible
    0.06
    grimas
    0.06
     giác
    0.06
     resto
    0.06
    격
    0.06
     graça
    0.06
    ening
    0.06
    Activations Density 0.017%

    No Known Activations