© 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. 19311
    Prev
    Next
    INDEX
    Explanations

    superpower

    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
     auxili
    -0.06
    ledi
    -0.05
    Ãłng
    -0.05
    ules
    -0.05
    æĴĴ
    -0.05
    oles
    -0.05
    红å°ĺ
    -0.05
    kais
    -0.05
     isVisible
    -0.05
     ce
    -0.05
    POSITIVE LOGITS
    大æīĭ
    0.06
    ernih
    0.06
    âĢ¦,
    0.06
     }\
    0.06
    altura
    0.06
     “âĢ¦
    0.06
    é¦ĭ
    0.05
    awat
    0.05
    èĪįä¸įå¾Ĺ
    0.05
    âĢ¦]
    0.05
    Activations Density 0.003%

    No Known Activations