© 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. 19694
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    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
    dej
    -0.07
    uler
    -0.06
    ones
    -0.06
    uj
    -0.06
    rej
    -0.06
    ymp
    -0.06
    ç½ijéĢļ
    -0.06
    æľŁéĹ´å±¥è¡Į
    -0.06
    hers
    -0.05
    ApiKey
    -0.05
    POSITIVE LOGITS
    allo
    0.06
    æ·±åĬłå·¥
    0.05
    ary
    0.05
    æĿ¡
    0.05
     bath
    0.05
    ullo
    0.05
    æĢĿ
    0.05
    æ¢Ŀ
    0.05
    ÑĥÑģ
    0.05
    ietta
    0.05
    Activations Density 0.013%

    No Known Activations