© 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. 19513
    Prev
    Next
    INDEX
    Explanations

    processes ending in -ing or -ization

    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
    ×Ŀ
    -0.06
    åĴĮè¦ģæ±Ĥ
    -0.06
    nitz
    -0.06
    åıĬè¦ģæ±Ĥ
    -0.06
    를
    -0.05
    agia
    -0.05
    agi
    -0.05
    壮çļĦ
    -0.05
    calcul
    -0.05
    niÄį
    -0.05
    POSITIVE LOGITS
    ç±»åŀĭ
    0.06
     impi
    0.05
    ů
    0.05
    onda
    0.05
    ová
    0.05
    æĸ¹åIJijåıijå±ķ
    0.05
    æ¯ıä¸Ģ个人çļĦ
    0.05
    ä¸Ģ个人çļĦ
    0.05
    ike
    0.05
    ice
    0.05
    Activations Density 0.114%

    No Known Activations