© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19641
    Prev
    Next
    INDEX
    Explanations

    market-based, market-driven

    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
    女éĥİ
    -0.06
    träger
    -0.06
    isir
    -0.06
    ocy
    -0.05
     sleeper
    -0.05
    女æĺŁ
    -0.05
     maturity
    -0.05
     vulnerability
    -0.05
    ellig
    -0.05
    commit
    -0.05
    POSITIVE LOGITS
    gre
    0.07
    strict
    0.06
    è¯ļä¿¡
    0.06
    èĩªåıij
    0.06
    ussen
    0.06
     organ
    0.06
    Ùĥر
    0.06
    å¢ŀåĢ¼
    0.05
    à¹Ħว
    0.05
     brisk
    0.05
    Activations Density 0.007%

    No Known Activations