© 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. 20522
    Prev
    Next
    INDEX
    Explanations

    foreign words and programming terms

    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
    iac
    -0.05
    é»ĺ
    -0.05
    .Dot
    -0.05
    erie
    -0.05
    ÉĻrÉĻ
    -0.05
    ulier
    -0.05
     Died
    -0.05
     Port
    -0.05
    errar
    -0.05
    jn
    -0.05
    POSITIVE LOGITS
     <+
    0.06
    并æĬĬ
    0.06
    oczy
    0.05
    èĢĮä¸Ķæĺ¯
    0.05
     "_
    0.05
     participado
    0.05
    è°Īè°Ī
    0.05
    à¹ĩà¸Ħ
    0.05
    contre
    0.05
    ÑĢово
    0.05
    Activations Density 0.002%

    No Known Activations