© 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. 20525
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
    ipse
    -0.06
    tur
    -0.06
    éĶģ
    -0.05
     prominent
    -0.05
    主æµģ
    -0.05
     mainstream
    -0.05
    hone
    -0.05
    atur
    -0.05
    awan
    -0.05
    æİ©
    -0.05
    POSITIVE LOGITS
    acar
    0.06
    æĹ¥ä»¥æĿ¥
    0.06
    ily
    0.06
    quoi
    0.05
     bols
    0.05
    ält
    0.05
    ä¹ħçļĦ
    0.05
     chill
    0.05
     hail
    0.05
    Appending
    0.05
    Activations Density 0.015%

    No Known Activations