© 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. 19350
    Prev
    Next
    INDEX
    Explanations

    `<applicable to`

    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
    кок
    -0.06
    romatic
    -0.06
    ÙĪار
    -0.06
    å¹´ç»ıéªĮ
    -0.06
    аÑĤÑĥ
    -0.06
    iliz
    -0.06
    ania
    -0.05
    воло
    -0.05
    Ïģίζει
    -0.05
    å¤ŁçĶ¨
    -0.05
    POSITIVE LOGITS
    eny
    0.05
    elper
    0.05
    pha
    0.05
    elman
    0.05
    ¦
    0.05
    sons
    0.05
    æĺ¯ä¸Ģ次
    0.05
     previous
    0.05
    elum
    0.05
     themselves
    0.05
    Activations Density 0.001%

    No Known Activations