© 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. 22314
    Prev
    Next
    INDEX
    Explanations

    numbers 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
    çĮİ
    -0.05
    à¸ķ
    -0.05
     Gree
    -0.05
     Trit
    -0.05
     tens
    -0.05
    çī©
    -0.05
    ÑĤÑĢо
    -0.05
    opak
    -0.05
    åī©ä½Ļ
    -0.05
    èī²
    -0.05
    POSITIVE LOGITS
    åĩ¡
    0.06
    ãģĭãģķ
    0.06
    使çĶ¨æŶéĹ´
    0.06
    ycastle
    0.06
     averages
    0.06
    ocre
    0.06
    naval
    0.06
    并ç»ı
    0.06
    lacer
    0.06
     fizer
    0.06
    Activations Density 0.002%

    No Known Activations