© 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. 20629
    Prev
    Next
    INDEX
    Explanations

    countries and some us states

    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
    åĨįæ·»
    -0.06
    iran
    -0.06
    åŁŁ
    -0.06
    maf
    -0.06
    ìľ¼ë¡ľëĬĶ
    -0.06
    没æŶéĹ´
    -0.05
    为客æĪ·
    -0.05
    .signals
    -0.05
    ance
    -0.05
    æķĻå¸ĪçļĦ
    -0.05
    POSITIVE LOGITS
    åľ¨åIJĦ
    0.05
    çĽĸ
    0.05
    尽管
    0.05
    ashington
    0.05
    éŁ
    0.05
    å¼Ģ头
    0.05
    uro
    0.05
    à·Ĭය
    0.05
    å¾·åįİ
    0.05
    ÑĨио
    0.05
    Activations Density 0.048%

    No Known Activations