© 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. 18876
    Prev
    Next
    INDEX
    Explanations

    complex situations and concepts

    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
    ãģ£ãģ¨
    -0.06
    åĴĮæĿİ
    -0.06
    vent
    -0.06
    ocrat
    -0.06
     thêm
    -0.05
    illary
    -0.05
    å°±ä¸Ĭ
    -0.05
    embr
    -0.05
    æŃ£å¼ı
    -0.05
    天çĶŁ
    -0.05
    POSITIVE LOGITS
    空空
    0.06
    Ø®ÙĦÙĤ
    0.05
    rex
    0.05
     grips
    0.05
    åħ¨è¿ĩç¨ĭ
    0.05
    çĶŁæ´»ä¹łæĥ¯
    0.05
     kav
    0.05
    zony
    0.05
    iskey
    0.05
    kans
    0.05
    Activations Density 0.003%

    No Known Activations