© 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. 19900
    Prev
    Next
    INDEX
    Explanations

    CWE checkpoint inhibitors

    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
    eliac
    -0.06
    ç³¾
    -0.06
    åį·åħ¥
    -0.05
    валÑĮ
    -0.05
    Ñĩайно
    -0.05
    aja
    -0.05
    çĶ¢çĶŁçļĦ
    -0.05
    ãģªãģĦãģ¨
    -0.05
    å¼ĢäºĨ
    -0.05
    ä¸Ģè¶Ł
    -0.05
    POSITIVE LOGITS
     verbre
    0.06
    æİ©
    0.06
    tridge
    0.06
    chez
    0.05
    æļ«
    0.05
    æļĤ
    0.05
    çī©è´¨
    0.05
     Goed
    0.05
     substance
    0.05
    æĦıè§ģ
    0.05
    Activations Density 0.003%

    No Known Activations