© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21807
    Prev
    Next
    INDEX
    Explanations

    approximately, roughly, largely, nearly

    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
    ždy
    -0.06
    icket
    -0.06
    ÃŃž
    -0.06
     ÙĥÙıÙĦ
    -0.06
    æĻļ
    -0.06
    ç¡®
    -0.06
    _ALL
    -0.06
     self
    -0.06
    ä¸Ģ女
    -0.06
    æ¯ıä¸Ģ
    -0.05
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.10
     approximately
    0.08
    approximately
    0.07
     largely
    0.07
    æĪĸå°ij
    0.06
    è¾ĥ强
    0.06
     roughly
    0.06
     Approximately
    0.06
    è¾ĥå¤ļ
    0.06
     nearly
    0.06
    Activations Density 0.171%

    No Known Activations