© 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. 16990
    Prev
    Next
    INDEX
    Explanations

    foreign, quote, true, not

    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
    ging
    -0.05
    imer
    -0.05
    çŃīçĿĢ
    -0.04
    trial
    -0.04
     N
    -0.04
    anti
    -0.04
    å¸ļ
    -0.04
    dach
    -0.04
    onic
    -0.04
     level
    -0.04
    POSITIVE LOGITS
    uron
    0.07
    åIJĮæŶå°Ĩ
    0.07
    betrieb
    0.07
    ä¸įæį¢
    0.07
    æĬ¥åijĬåĴĮ
    0.07
    继ç»Ń沿
    0.06
    icter
    0.06
    urato
    0.06
    tienen
    0.06
    olim
    0.06
    Activations Density 0.001%

    No Known Activations