© 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. 18795
    Prev
    Next
    INDEX
    Explanations

    the noun phrase

    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
    à¹ĩà¸ķ
    -0.06
    gul
    -0.06
     Iglesias
    -0.06
    ÙĪرÙĬا
    -0.06
    Advisor
    -0.06
    atika
    -0.06
     kori
    -0.06
    kör
    -0.06
    гоÑĢод
    -0.05
    atik
    -0.05
    POSITIVE LOGITS
    æĬĬ人
    0.06
    andu
    0.05
    åѦçłĶ究
    0.05
    aves
    0.05
    å¼ºåĽ½
    0.05
    Ñĥв
    0.05
    ography
    0.05
    è¦ģæ±Ĥåľ¨
    0.05
    éri
    0.05
    ÑĮÑİ
    0.05
    Activations Density 0.015%

    No Known Activations