© 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. 18901
    Prev
    Next
    INDEX
    Explanations

    president, Fraser, her, coaches, produced

    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
    ptom
    -0.06
    tian
    -0.06
    头èĦij
    -0.06
    ä¸įåħ¥
    -0.06
    åĢĴæĺ¯
    -0.06
    åĢ¾åIJij
    -0.06
     dụ
    -0.05
    åŁºæľ¬åİŁåĪĻ
    -0.05
    aim
    -0.05
    shot
    -0.05
    POSITIVE LOGITS
    aksi
    0.05
     dang
    0.05
     acolo
    0.05
    appiness
    0.05
    åĪ«å¿ĺäºĨ
    0.05
    æ¯įè¯Ń
    0.05
     surpass
    0.05
     crem
    0.05
    ollen
    0.05
    å°ģ
    0.05
    Activations Density 0.002%

    No Known Activations