© 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. 19600
    Prev
    Next
    INDEX
    Explanations

    Tory Blog, comedy, teen, couples

    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
    вок
    -0.06
    æĸ¹
    -0.06
    λÏįÏĦε
    -0.05
     rinn
    -0.05
    éľ
    -0.05
    åĴª
    -0.05
     Aufwand
    -0.05
    wiÄĻ
    -0.05
    asil
    -0.05
    ilig
    -0.05
    POSITIVE LOGITS
     quen
    0.07
    hog
    0.06
    ively
    0.06
    ÑĪо
    0.05
    ä¹ĥèĩ³
    0.05
    以èĩ³
    0.05
    ä½ĨåIJĮæŶ
    0.05
    ëį°
    0.05
    rafa
    0.05
     stock
    0.05
    Activations Density 0.024%

    No Known Activations