© 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. 18955
    Prev
    Next
    INDEX
    Explanations

    life and personality

    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
    çļĦ好å¤Ħ
    -0.06
    æ¯ĶçļĦ
    -0.06
    (nextProps
    -0.06
     classic
    -0.06
    çĸijä¼¼
    -0.06
     Pela
    -0.05
    被称为
    -0.05
    arms
    -0.05
    amel
    -0.05
    西å¼ı
    -0.05
    POSITIVE LOGITS
     bersangkutan
    0.06
     esfuer
    0.06
    leme
    0.05
     ë°ĺìĺģ
    0.05
     homenaje
    0.05
     #-
    0.05
    æĦıæĦ¿
    0.05
    測
    0.05
     chứ
    0.05
     sekaligus
    0.05
    Activations Density 0.034%

    No Known Activations