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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19636
    Prev
    Next
    INDEX
    Explanations

    year

    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
    æģº
    -0.06
    tico
    -0.06
    éķ¿æķĪ
    -0.06
    ç²ĹæĶ¾
    -0.06
    nÄĻ
    -0.06
    ee
    -0.06
    opper
    -0.05
    lace
    -0.05
    æĪĸä¸İ
    -0.05
    éķ¿æľŁ
    -0.05
    POSITIVE LOGITS
    ucc
    0.06
    åĪ·æĸ°
    0.06
    çĦķ
    0.06
    ibus
    0.05
    udas
    0.05
    edan
    0.05
     ArrayBuffer
    0.05
     anew
    0.05
     Succ
    0.05
    æĸ°çļĦæĮijæĪĺ
    0.05
    Activations Density 0.048%

    No Known Activations