© 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. 18635
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and definitions

    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
    ere
    -0.05
    ÛĮدÙĩ
    -0.05
    寰
    -0.05
     flush
    -0.05
    ct
    -0.04
    ley
    -0.04
     arbitrarily
    -0.04
    ä»İåı¤
    -0.04
    son
    -0.04
    rol
    -0.04
    POSITIVE LOGITS
    istribu
    0.07
    InputModule
    0.06
    èĢĮçĶŁ
    0.06
    LEC
    0.06
    elts
    0.06
    homes
    0.06
    istou
    0.06
    สัà¸ķ
    0.06
    benh
    0.06
    lecture
    0.06
    Activations Density 0.004%

    No Known Activations