© 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. 19795
    Prev
    Next
    INDEX
    Explanations

    enter key

    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
    èł
    -0.06
    los
    -0.06
    ä¸Ģèĩ³
    -0.06
    óÅĤ
    -0.06
    agnet
    -0.06
    Ø´ÙĨ
    -0.06
     زاÙĦت
    -0.06
    leks
    -0.06
    èĩªå·±çļĦ人
    -0.05
     coni
    -0.05
    POSITIVE LOGITS
    ilet
    0.06
    inal
    0.06
    yen
    0.06
    é½IJ
    0.05
     auton
    0.05
    æĤ¯
    0.05
    emann
    0.05
    seed
    0.05
    åºŃ
    0.05
    icole
    0.05
    Activations Density 0.006%

    No Known Activations