© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18388
    Prev
    Next
    INDEX
    Explanations

    charged or sentenced

    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
    ç«£
    -0.07
    egiatan
    -0.06
    åĩ¡
    -0.06
    æĦıåĽ¾
    -0.06
    omé
    -0.06
    å¼ĢçĿĢ
    -0.06
    ãģıãĤĬ
    -0.06
    å¤ĩ
    -0.06
    符
    -0.06
    å¾Ģ常ä¸Ģæł·
    -0.06
    POSITIVE LOGITS
    uris
    0.05
    lements
    0.05
    æ±IJ
    0.05
    åģ¥åº·çĶŁæ´»
    0.05
    ounder
    0.05
     ater
    0.05
    доÑħ
    0.05
    å¼łå°ı
    0.05
    .URL
    0.05
    大河
    0.05
    Activations Density 0.055%

    No Known Activations