© 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. 19061
    Prev
    Next
    INDEX
    Explanations

    as an argument

    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
    pper
    -0.06
    Ø·ÙĦ
    -0.06
    ain
    -0.06
    èĮĥåĦ¿
    -0.06
    ä¼Ĺå¤ļ
    -0.06
    eni
    -0.05
    ä»ij
    -0.05
    odzi
    -0.05
    赶
    -0.05
     аÑĢен
    -0.05
    POSITIVE LOGITS
    樣çļĦ
    0.05
    late
    0.05
    åŁºåľ°å»ºè®¾
    0.05
    åĥ¹
    0.05
    avin
    0.05
    itrine
    0.05
    ÙĬزة
    0.05
    æľīçļĦ
    0.05
    -ing
    0.05
    lim
    0.05
    Activations Density 0.002%

    No Known Activations