© 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. 19050
    Prev
    Next
    INDEX
    Explanations

    US states, countries, or cities

    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
    æ³¢çī¹
    -0.06
    è¿ĩåħ³
    -0.06
    azon
    -0.06
    izzi
    -0.06
     aide
    -0.05
    оеди
    -0.05
    lard
    -0.05
     aren
    -0.05
    _subtype
    -0.05
     isn
    -0.05
    POSITIVE LOGITS
    款
    0.06
    env
    0.06
    ebab
    0.06
    è·Į
    0.05
    款çļĦ
    0.05
    -serif
    0.05
    æľ¯è¯Ń
    0.05
    ä¹ĭå·®
    0.05
    ä¹ĭçİĭ
    0.05
     abs
    0.05
    Activations Density 0.157%

    No Known Activations