© 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. 16552
    Prev
    Next
    INDEX
    Explanations

    code punctuation or identifiers

    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
    ay
    -0.06
    anks
    -0.05
    zers
    -0.05
    èĤ¡å¸Ĥåľº
    -0.05
    è½´
    -0.05
    :`~
    -0.05
    çĶĺ
    -0.05
    eso
    -0.05
    ämpft
    -0.05
     Serial
    -0.05
    POSITIVE LOGITS
    estro
    0.06
    Ð¢ÐŁ
    0.06
    star
    0.06
    ÑĢаÑĨиÑı
    0.06
    ’T
    0.06
    ssp
    0.06
    JC
    0.06
    %M
    0.06
    ä¸Ģç«ł
    0.06
     surpre
    0.06
    Activations Density 0.037%

    No Known Activations