© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    endings or continuations

    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
     synonymous
    -0.06
    æİ
    -0.05
    è¿ĺä¸įæĺ¯
    -0.05
    weg
    -0.05
    Ùĥا
    -0.05
     t
    -0.05
    faz
    -0.05
    åľ¨è¿ĻäºĽ
    -0.05
     A
    -0.05
    wizard
    -0.05
    POSITIVE LOGITS
    Anc
    0.07
    thon
    0.06
    ends
    0.06
     certainly
    0.05
    end
    0.05
    ä¸ĢèĪ¬éĥ½ä¼ļ
    0.05
    é¡»
    0.05
     pouss
    0.05
    æľī好
    0.05
    eppe
    0.05
    Activations Density 0.001%

    No Known Activations