© 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. 17830
    Prev
    Next
    INDEX
    Explanations

    sugar beet

    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
    ys
    -0.06
    åľ°åĴĮ
    -0.05
    avas
    -0.05
    设计
    -0.05
    acting
    -0.05
     Vict
    -0.05
    dic
    -0.05
    ëĮĢ
    -0.05
    ully
    -0.05
    equ
    -0.05
    POSITIVE LOGITS
     **.**
    0.06
    bahan
    0.06
    åĬŀæ³ķ
    0.06
     times
    0.06
    ften
    0.06
    erbe
    0.06
    å±ŀ
    0.05
     Times
    0.05
     foot
    0.05
    Extras
    0.05
    Activations Density 0.016%

    No Known Activations