© 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. 20778
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
     herald
    -0.05
    lande
    -0.05
     terminal
    -0.05
    agra
    -0.05
    横
    -0.05
    vád
    -0.05
    équ
    -0.05
     emanc
    -0.05
    åįİåºľ
    -0.05
    avirus
    -0.05
    POSITIVE LOGITS
    ¿
    0.06
    æĭŁ
    0.06
    èĩªå·±æĥ³è¦ģ
    0.06
     Scopri
    0.06
    æĺ¯ç»ı
    0.06
    ä»İåīį
    0.05
    ÑģÑĤв
    0.05
    ÑĪÑĤ
    0.05
    æ¢ħ
    0.05
     compromis
    0.05
    Activations Density 0.012%

    No Known Activations