© 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. 18233
    Prev
    Next
    INDEX
    Explanations

    previous; preceding; upstream

    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
     future
    -0.06
    lett
    -0.06
    ç§Ģæīį
    -0.06
    лежа
    -0.06
    èĪĮ
    -0.06
    æľªæĿ¥
    -0.06
    future
    -0.05
    æľªä¾Ĩ
    -0.05
    kamp
    -0.05
    nehmer
    -0.05
    POSITIVE LOGITS
    previous
    0.06
    ä¸Ĭä¸Ģ个
    0.06
     пÑĢедÑĭ
    0.06
    Prev
    0.06
    ä¸Ĭä¸Ģ
    0.06
     Previous
    0.06
    è¾Ī
    0.06
    Previous
    0.06
    åīįä¸Ģ
    0.06
     preceding
    0.06
    Activations Density 0.054%

    No Known Activations