© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 19537
    Prev
    Next
    INDEX
    Explanations

    change, adapt, control, vary

    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
    gies
    -0.06
    amel
    -0.06
    cription
    -0.06
    ÑģÑĤиÑĤÑĥ
    -0.06
    ioni
    -0.06
     Airways
    -0.06
    arts
    -0.06
    cioni
    -0.06
     personal
    -0.06
    loff
    -0.06
    POSITIVE LOGITS
    undu
    0.06
    åIJĥåIJĥ
    0.06
    æĦıçļĦ
    0.05
    åĺ´
    0.05
     exped
    0.05
    ä½ķ
    0.05
    esub
    0.05
    enstr
    0.05
     mega
    0.05
    eve
    0.05
    Activations Density 0.003%

    No Known Activations