© 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. 18803
    Prev
    Next
    INDEX
    Explanations

    top lists

    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
     ulang
    -0.06
    oga
    -0.05
    ļľ
    -0.05
    accro
    -0.05
    æĪIJç«ł
    -0.05
    мна
    -0.05
    cest
    -0.05
    ierer
    -0.05
    ìĤ¬ìĿ¼
    -0.05
    braco
    -0.05
    POSITIVE LOGITS
    ray
    0.06
    çIJ³
    0.05
    lem
    0.05
    úk
    0.05
    è¶ĭ
    0.05
    xs
    0.05
     Ef
    0.05
    ÑĢавни
    0.05
    yk
    0.05
    IX
    0.05
    Activations Density 0.009%

    No Known Activations