© 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. 20049
    Prev
    Next
    INDEX
    Explanations

    functional equations or entities

    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
    icana
    -0.06
    à¹Ħà¸Ķà¹īวà¹Īา
    -0.06
    icka
    -0.06
    chaffen
    -0.05
    çº¢é¢ľ
    -0.05
     phúc
    -0.05
     gebe
    -0.05
    æ¼ı
    -0.05
    owitz
    -0.05
    othy
    -0.05
    POSITIVE LOGITS
     instead
    0.07
    instead
    0.07
    åīįæıIJæĺ¯
    0.06
     appunto
    0.06
    aja
    0.06
    æķ°æĺ¯
    0.06
    尤为
    0.06
    æĪIJåĪĨæĺ¯
    0.05
    æ¯ıéļĶ
    0.05
    缮æłĩæĺ¯
    0.05
    Activations Density 0.137%

    No Known Activations