© 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. 21757
    Prev
    Next
    INDEX
    Explanations

    oxidation and its derivatives

    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
    uggy
    -0.06
     ÑħолодилÑĮник
    -0.06
    bidden
    -0.06
    åIJ¬äºĨ
    -0.05
    urgent
    -0.05
    ered
    -0.05
    åĴĮéĺ¿
    -0.05
    æijĩæijĨ
    -0.05
     Daarna
    -0.05
    ing
    -0.05
    POSITIVE LOGITS
    oxid
    0.06
    迹
    0.06
    xid
    0.06
     oxid
    0.06
    Capture
    0.06
    幸
    0.06
    ole
    0.06
    ä¸Ĭä¸Ģå±Ĥ楼
    0.06
     Marina
    0.06
    åħ¬åħģ
    0.06
    Activations Density 0.025%

    No Known Activations