© 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. 19584
    Prev
    Next
    INDEX
    Explanations

    what

    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
    ubbo
    -0.05
    imary
    -0.05
    werke
    -0.05
    寫çļĦ
    -0.05
    COPY
    -0.05
     mur
    -0.05
    findFirst
    -0.05
    gege
    -0.05
     adverse
    -0.05
    attet
    -0.05
    POSITIVE LOGITS
    èĽ
    0.06
    å¥Ī
    0.06
    åı¯æĥ³
    0.05
    å¼ķ
    0.05
    UCK
    0.05
    Breadcrumb
    0.05
     literal
    0.05
    KB
    0.05
    onica
    0.05
    avier
    0.05
    Activations Density 0.002%

    No Known Activations