© 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. 19740
    Prev
    Next
    INDEX
    Explanations

    season statistics

    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
    hyl
    -0.06
    èĪĮ
    -0.06
    èĵĦ
    -0.06
    ÙĩÙĦ
    -0.05
    åİĭ
    -0.05
    ushi
    -0.05
    èĩ³é«ĺ
    -0.05
     alo
    -0.04
     unknow
    -0.04
    åĩºèº«
    -0.04
    POSITIVE LOGITS
    atest
    0.07
    uard
    0.06
    awn
    0.06
    mek
    0.06
     martedì
    0.06
    æ¼ĵ
    0.06
    onta
    0.06
    ừa
    0.06
    ikator
    0.05
    éĤ£ä¸¤ä¸ª
    0.05
    Activations Density 0.059%

    No Known Activations