© 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. 19690
    Prev
    Next
    INDEX
    Explanations

    so, hence, but, however

    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
    缮çļĦ
    -0.06
    æĽ´æľī
    -0.06
    å¯Įæľī
    -0.05
    缸éĤ»
    -0.05
    çĽĸ
    -0.05
    ä¾ĭå¦Ĥ
    -0.05
    åIJĪåIJĮ
    -0.05
    alcon
    -0.05
    ä¸įåłª
    -0.05
    omatis
    -0.05
    POSITIVE LOGITS
     typical
    0.07
    ä¾Ŀè§Ħ
    0.06
    ä¸įèĭŁ
    0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    0.06
    æĮīçħ§è§Ħå®ļ
    0.06
    ä¸ĭéĿ¢æĺ¯
    0.06
    æ¶ķ
    0.06
    éĢļå¸¸åľ¨
    0.06
    æł¹æ·±
    0.06
     tÃŃp
    0.06
    Activations Density 0.084%

    No Known Activations