© 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. 21099
    Prev
    Next
    INDEX
    Explanations

    praying for blessings or peace

    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
     erog
    -0.06
    quanto
    -0.06
    ÅĤek
    -0.06
    à¸Īà¸ĩ
    -0.06
    æĪĸéĥ¨åĪĨ
    -0.06
    лива
    -0.06
     colectiv
    -0.05
    казаниÑı
    -0.05
     punt
    -0.05
    obia
    -0.05
    POSITIVE LOGITS
    åĴĮæĶ¹åĸĦ
    0.05
    end
    0.05
     moj
    0.05
    ä¸įåİ»
    0.05
    اس
    0.05
    Wer
    0.05
    éģ¿åħį
    0.05
    ç»´æĬ¤
    0.05
    usement
    0.05
    aret
    0.05
    Activations Density 0.013%

    No Known Activations