© 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. 19628
    Prev
    Next
    INDEX
    Explanations

    when i run

    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
    å¾Ħ
    -0.05
    ichel
    -0.05
    åĩ¸
    -0.05
    认è¯Ĩ
    -0.05
    ersistence
    -0.05
     experiment
    -0.05
     impress
    -0.05
    æłĸ
    -0.05
    ä¼ĺäºİ
    -0.05
     incumbent
    -0.05
    POSITIVE LOGITS
    ongan
    0.06
    antes
    0.06
    رÙĪÙģ
    0.06
    æ°ijè¿Ľ
    0.06
    RB
    0.06
    innan
    0.06
     natür
    0.06
    ANTES
    0.06
    oro
    0.06
    绣èĬ±
    0.06
    Activations Density 0.016%

    No Known Activations