© 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. 21419
    Prev
    Next
    INDEX
    Explanations

    imperative calls to action

    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
    èī²ãģĮ
    -0.06
    oes
    -0.06
    åĽĽå¹³
    -0.06
    山大
    -0.06
    garan
    -0.06
    боли
    -0.06
    ïque
    -0.06
    æĺŁäºº
    -0.06
    æĪIJ为ä¸Ģ个
    -0.06
    μÏĢ
    -0.06
    POSITIVE LOGITS
    ÙIJÙij
    0.05
    ä¸ĩèµ·
    0.05
     yourself
    0.05
    enschaft
    0.05
    çİ
    0.05
    æł·
    0.05
     (*
    0.04
    Base
    0.04
    D
    0.04
     yourselves
    0.04
    Activations Density 0.060%

    No Known Activations