© 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. 20667
    Prev
    Next
    INDEX
    Explanations

    confidence id env

    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
     пода
    -0.06
    åľ¨åħ¶
    -0.06
    боÑĢом
    -0.06
    neau
    -0.06
     بÙĨدÛĮ
    -0.05
     اÙĦØŃاÙĦ
    -0.05
     jednos
    -0.05
    hund
    -0.05
    vende
    -0.05
    [,]
    -0.05
    POSITIVE LOGITS
    ä¼Ĺ
    0.07
    uelle
    0.06
    å°ģ
    0.05
    wards
    0.05
    acula
    0.05
    ä¸Ģå®ļç¨ĭ度
    0.05
    æ¸Ĭ
    0.05
    ness
    0.05
    iks
    0.05
     immersion
    0.05
    Activations Density 0.008%

    No Known Activations