© 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. 21418
    Prev
    Next
    INDEX
    Explanations

    question words and "and"

    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
    æĴ
    -0.05
    ×Ļ×ķ
    -0.05
    èĩªå·±çļĦåĬĽéĩı
    -0.05
    اÙĩ
    -0.05
    uil
    -0.05
    ανε
    -0.05
    гой
    -0.05
    ÑģÑĮко
    -0.05
    enso
    -0.04
    ycl
    -0.04
    POSITIVE LOGITS
    åħ¬åı¸ä¸º
    0.07
    åħ¬åı¸å°Ĩ
    0.06
    çļĦåİ»
    0.06
    èĢĮè¦ģ
    0.06
    夥
    0.06
    cab
    0.06
    åįģäºĮæĮĩ
    0.05
    èĢĮèµ·
    0.05
    ئÙĩ
    0.05
    èŃ½
    0.05
    Activations Density 0.031%

    No Known Activations