© 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. 19664
    Prev
    Next
    INDEX
    Explanations

    committed to, dedicated to

    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
    annies
    -0.06
    rens
    -0.06
    enties
    -0.06
    -inverse
    -0.05
    erties
    -0.05
    çĿĢæĢ¥
    -0.05
    done
    -0.05
    ettata
    -0.05
    cia
    -0.05
     Darkness
    -0.05
    POSITIVE LOGITS
    воло
    0.05
    请éĢīæĭ©
    0.05
    çIJĨ论çļĦ
    0.05
     ÑĨелоÑģÑĤ
    0.05
    ebo
    0.05
    走好
    0.05
    ipl
    0.05
    æĬĹ
    0.05
     presence
    0.05
    å®īæİĴçļĦ
    0.05
    Activations Density 0.006%

    No Known Activations