© 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. 19084
    Prev
    Next
    INDEX
    Explanations

    narrative texts or perspectives

    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
    er
    -0.09
    liness
    -0.05
    ä¹ĥ
    -0.05
     notable
    -0.05
    ×ķ
    -0.05
    åĴĮçĪ±
    -0.05
    éph
    -0.05
    ments
    -0.05
    how
    -0.05
    erait
    -0.05
    POSITIVE LOGITS
    gili
    0.07
    å¤ļåĽ¾
    0.07
    Ñĩей
    0.07
    odio
    0.07
    INU
    0.07
    iato
    0.07
    uschen
    0.07
    /bg
    0.07
     ÄijÃŃch
    0.07
    uez
    0.07
    Activations Density 0.003%

    No Known Activations