© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20161
    Prev
    Next
    INDEX
    Explanations

    first of something

    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
    ame
    -0.07
    eiro
    -0.06
    eiros
    -0.06
    äºĭæĪIJ
    -0.06
    ä¸Ģå®ļçļĦ
    -0.06
    ä¸įå®Įåħ¨
    -0.06
     Ame
    -0.06
    çļĦä¸ĢæŃ¥
    -0.06
    å°¼æĸ¯
    -0.05
    大åĪĢ
    -0.05
    POSITIVE LOGITS
    å¾Ģ
    0.05
    اÛĮت
    0.05
    æľ¬æľº
    0.05
    clin
    0.05
     contingent
    0.05
     ÙĦÙħ
    0.05
    ÙĦÙħ
    0.05
    åIJij
    0.05
    ì¶Ķ
    0.05
    ayan
    0.05
    Activations Density 0.033%

    No Known Activations