© 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. 20674
    Prev
    Next
    INDEX
    Explanations

    food descriptions

    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
    arian
    -0.05
     пиÑīе
    -0.05
    map
    -0.05
    кон
    -0.05
    å¤©çľ¼
    -0.05
    adian
    -0.05
    å®ŀæĸ½
    -0.05
    è¦ģ件
    -0.05
     limit
    -0.05
     souhaitent
    -0.05
    POSITIVE LOGITS
    æİĸ
    0.07
    urai
    0.07
    çĹ
    0.07
    ثر
    0.07
    端æŃ£
    0.06
    بت
    0.06
    è¾¾æĭī
    0.06
    ä¸įæ±Ĥ
    0.06
     Burning
    0.06
    navbarSupportedContent
    0.06
    Activations Density 0.010%

    No Known Activations