© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19739
    Prev
    Next
    INDEX
    Explanations

    class name and scope

    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
    abl
    -0.05
    寸
    -0.05
     Vielf
    -0.05
     pozn
    -0.05
    ucker
    -0.05
    ед
    -0.05
    ry
    -0.05
    åıĤåĬłäºĨä¼ļè®®
    -0.05
     nghiá»ĩp
    -0.05
    Ùĩرة
    -0.05
    POSITIVE LOGITS
     Alta
    0.06
    alet
    0.06
    è¾ľ
    0.06
    amol
    0.06
    她们
    0.06
    壮çļĦ
    0.06
     درب
    0.06
    alism
    0.06
    arbon
    0.06
    åĽĽäºĶ
    0.05
    Activations Density 0.055%

    No Known Activations