© 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. 16841
    Prev
    Next
    INDEX
    Explanations

    follows "the"

    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
    ctest
    -0.06
    æĥĬ
    -0.06
    丢
    -0.05
    -ra
    -0.05
    -corner
    -0.05
    elper
    -0.05
    ç¨Ģ
    -0.05
    رÙĪÛĮ
    -0.05
    صرÙĬ
    -0.05
     Larson
    -0.05
    POSITIVE LOGITS
    çħŀ
    0.06
    į
    0.06
    abal
    0.06
     quit
    0.05
    è¿IJè¡Į
    0.05
    istik
    0.05
    ä¸įèµ·
    0.05
     included
    0.05
    hub
    0.05
    avl
    0.05
    Activations Density 0.001%

    No Known Activations