© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21435
    Prev
    Next
    INDEX
    Explanations

    presenting information or stating position

    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
     poussi
    -0.06
    reiz
    -0.06
    راÙĩ
    -0.06
    رÛĮÙĤ
    -0.06
    czÄħ
    -0.05
    ulti
    -0.05
     Vorg
    -0.05
    ermen
    -0.05
    kori
    -0.05
    ä¸īå¹´åĨħ
    -0.05
    POSITIVE LOGITS
    åĪ°ä½ł
    0.05
    éģį
    0.05
    eman
    0.05
    è¦ģ注æĦıçļĦæĺ¯
    0.05
    èĽĭ
    0.05
    ிரà¯ģ
    0.05
    unen
    0.05
    å¼
    0.05
    aios
    0.05
    firm
    0.05
    Activations Density 0.006%

    No Known Activations