© 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. 16882
    Prev
    Next
    INDEX
    Explanations

    questions and punctuation

    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
    lik
    -0.06
    inkle
    -0.06
    èĭij
    -0.05
    ר×Ĺ
    -0.05
    atar
    -0.05
    elos
    -0.05
    éĤ£æĺ¯åĽłä¸º
    -0.05
     uncomp
    -0.05
    åѦçĶŁ
    -0.05
    ç»ıåķĨ
    -0.05
    POSITIVE LOGITS
    åŃ½
    0.06
    зда
    0.06
    deen
    0.06
    ermen
    0.06
    ôm
    0.06
    ./(
    0.05
    onnen
    0.05
    gnos
    0.05
    erno
    0.05
    coma
    0.05
    Activations Density 0.011%

    No Known Activations