© 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. 20471
    Prev
    Next
    INDEX
    Explanations

    rarely, possible, exceeds

    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
     Parks
    -0.06
    åĨ³å®ļæĺ¯åIJ¦
    -0.06
    ä¸İçłĶ究
    -0.06
     anders
    -0.06
    çłĶ究ä¸Ń
    -0.05
    iger
    -0.05
    asu
    -0.05
    ezu
    -0.05
    intang
    -0.05
     Invisible
    -0.05
    POSITIVE LOGITS
    çķĻ念
    0.06
    ä¼ı
    0.06
    ç½®
    0.06
    ä¸Ģå®ļçļĦ
    0.06
     dou
    0.05
    аÑĩ
    0.05
    sav
    0.05
     sav
    0.05
     express
    0.05
    称
    0.05
    Activations Density 0.008%

    No Known Activations