© 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. 17711
    Prev
    Next
    INDEX
    Explanations

    duck plague, dynasty, hepatitis, boots

    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
     cig
    -0.06
    ÙĤÙī
    -0.06
    ürg
    -0.06
    oroz
    -0.06
    гÑĥÑĤ
    -0.06
     Ruhr
    -0.06
    нÑĥÑĤÑĢи
    -0.05
    zuki
    -0.05
    icate
    -0.05
    fang
    -0.05
    POSITIVE LOGITS
    ons
    0.06
    ÑģÑı
    0.06
    ؤÙĦاء
    0.06
    جع
    0.06
    ÙĨاÙħÙĩ
    0.06
    boarding
    0.06
    ingham
    0.05
    o
    0.05
    oning
    0.05
    é¹ħ
    0.05
    Activations Density 0.003%

    No Known Activations