© 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. 17634
    Prev
    Next
    INDEX
    Explanations

    masses, structures, regions, protein

    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
    ynd
    -0.07
    **–
    -0.06
    åı¥è¯Ŀ说
    -0.06
    erma
    -0.06
    çĭĻ
    -0.06
    estina
    -0.06
    ลาย
    -0.06
    该类
    -0.06
    ]-$
    -0.06
    usakan
    -0.06
    POSITIVE LOGITS
    è°ĵä¹ĭ
    0.05
    以为æĺ¯
    0.05
    类似
    0.05
    å¾Īåĥı
    0.05
     representing
    0.05
    Ùħر
    0.05
    te
    0.05
     [
    0.05
    ç»ı
    0.05
    X
    0.05
    Activations Density 0.084%

    No Known Activations