© 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. 17690
    Prev
    Next
    INDEX
    Explanations

    culture and its formation

    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
    aat
    -0.06
    asan
    -0.06
    swer
    -0.06
    æĪļ
    -0.05
    elin
    -0.05
    ä¼į
    -0.05
     basics
    -0.05
    elines
    -0.05
    è´¨
    -0.05
    onnier
    -0.05
    POSITIVE LOGITS
    htar
    0.06
    Partial
    0.06
    ×¢×ĵ
    0.06
    磮
    0.06
    çªĦ
    0.06
    åķĵ
    0.06
    ä¹ħèĢĮä¹ħä¹ĭ
    0.06
     parti
    0.05
    ردÙĩ
    0.05
    Knife
    0.05
    Activations Density 0.008%

    No Known Activations