© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18896
    Prev
    Next
    INDEX
    Explanations

    selected values or items

    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
    a
    -0.07
    æĢ§åľ°
    -0.06
    seau
    -0.06
    ing
    -0.06
    æĢ§åĴĮ
    -0.05
    æĢ§çļĦ
    -0.05
    alet
    -0.05
    aufs
    -0.05
     Weise
    -0.05
    à¸ģวà¹Īา
    -0.05
    POSITIVE LOGITS
    дне
    0.08
    ÛĮÚº
    0.07
    ionen
    0.07
    egy
    0.07
    orros
    0.07
    ebet
    0.07
    éis
    0.07
    端çļĦ
    0.06
    hirt
    0.06
    ñado
    0.06
    Activations Density 0.011%

    No Known Activations