© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22092
    Prev
    Next
    INDEX
    Explanations

    Navigation Controller

    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
    wap
    -0.07
     ä»Ĭå¹´ãģ¯
    -0.06
    _reporting
    -0.06
    èĪĨ论
    -0.06
    assandra
    -0.06
    enheim
    -0.05
    urses
    -0.05
    ulai
    -0.05
    declar
    -0.05
    esting
    -0.05
    POSITIVE LOGITS
    umb
    0.05
     маÑĪи
    0.05
    Ñģлей
    0.05
    -o
    0.05
     perv
    0.05
    ye
    0.05
    ียà¸Ļ
    0.05
    draft
    0.05
    æĮºæĭĶ
    0.05
    ÙĥÙĨ
    0.05
    Activations Density 0.082%

    No Known Activations