© 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. 16621
    Prev
    Next
    INDEX
    Explanations

    URLs and titles

    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
    wiÅĽcie
    -0.06
    翼翼
    -0.06
    ноÑģÑĤÑĢан
    -0.06
    oglob
    -0.06
    èѬ
    -0.05
    izarre
    -0.05
    zyw
    -0.05
    êµīìŀ¥
    -0.05
    iego
    -0.05
    bole
    -0.05
    POSITIVE LOGITS
    Ùĩ
    0.10
    ãĥ³
    0.09
    Ñĥ
    0.07
    an
    0.07
    ers
    0.06
    Ñĥл
    0.06
    аÑİÑĤ
    0.06
    komp
    0.06
    rett
    0.06
    м
    0.06
    Activations Density 0.029%

    No Known Activations