© 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. 18812
    Prev
    Next
    INDEX
    Explanations

    importing libraries and modules

    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
    åį³æĹ¥
    -0.06
    第åįģåħ«
    -0.06
    æ²³éķĩ
    -0.06
    اÙĩÛĮ
    -0.06
     недоÑģÑĤ
    -0.06
     devid
    -0.06
    ÑĩаÑĤкÑĥ
    -0.06
     diventata
    -0.06
    etet
    -0.06
    oleon
    -0.06
    POSITIVE LOGITS
    æĦıæĢĿ
    0.06
    beck
    0.06
    caller
    0.05
    kre
    0.05
    jour
    0.05
     mere
    0.05
    æİ¢
    0.05
    ç¾½
    0.05
    ÙĪØ«
    0.05
     mach
    0.05
    Activations Density 0.030%

    No Known Activations