© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18224
    Prev
    Next
    INDEX
    Explanations

    died on/of/in

    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
     напо
    -0.06
    ниÑĩнÑĭй
    -0.06
    ×Ļ×Ļ×Ŀ
    -0.06
    Æ¡m
    -0.06
    izzo
    -0.06
     Ready
    -0.05
    ÙĬز
    -0.05
    ikker
    -0.05
    ниÑĩ
    -0.05
    loo
    -0.05
    POSITIVE LOGITS
     crunch
    0.06
    èļģ
    0.06
    ARA
    0.05
    AMA
    0.05
    æ°´
    0.05
     inadvert
    0.05
    æĪŁ
    0.05
    поÑĢÑĤа
    0.05
    å¾ĹæĿ¥
    0.05
    ç»ı
    0.05
    Activations Density 0.054%

    No Known Activations