© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19426
    Prev
    Next
    INDEX
    Explanations

    {

    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
     اÙĦÙĪ
    -0.06
    ä¸ĢèĪ¬èĢĮè¨Ģ
    -0.05
    å±ĪæĮĩ
    -0.05
    è´¹
    -0.05
    ild
    -0.05
    Фо
    -0.05
     ÑĦик
    -0.05
    iony
    -0.05
    ianza
    -0.04
    以ä¸ĭçļĦç½ļ款
    -0.04
    POSITIVE LOGITS
    é¦Ļå±±
    0.06
    ôme
    0.06
    noch
    0.06
     olor
    0.06
    USERNAME
    0.06
    ustin
    0.06
    OPP
    0.06
    Carthy
    0.06
    jat
    0.06
    xel
    0.06
    Activations Density 0.004%

    No Known Activations