© 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. 21885
    Prev
    Next
    INDEX
    Explanations

    and more

    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
    aign
    -0.06
    æĪijåIJ§
    -0.06
    ngle
    -0.06
    æĸ¹æ¡ĪåĴĮ
    -0.06
    nga
    -0.06
    shaw
    -0.06
    é¾Ħ
    -0.06
    aim
    -0.06
    rific
    -0.06
    ãģĽ
    -0.05
    POSITIVE LOGITS
     заÑģл
    0.05
    ÙħÙĥÙĨ
    0.05
     Äijảo
    0.05
     ninh
    0.05
    èĪī
    0.05
    ά
    0.05
    üst
    0.05
     prez
    0.05
    eltas
    0.05
     пÑĢигод
    0.05
    Activations Density 0.005%

    No Known Activations