© 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. 21385
    Prev
    Next
    INDEX
    Explanations

    JSON delimiters and structure

    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
    aul
    -0.05
    ä»»éĢī
    -0.05
     Goth
    -0.05
     Mang
    -0.05
     Twitch
    -0.05
    æĶ¾çľ¼
    -0.04
    ih
    -0.04
    Regardless
    -0.04
    oter
    -0.04
    egr
    -0.04
    POSITIVE LOGITS
    ä¸Ńå°ı
    0.06
     arp
    0.06
     Mancha
    0.06
     ÙĨÙĩا
    0.06
    天亮
    0.06
    าà¸Ĺี
    0.06
    æĬµ
    0.06
    ä¸Ńæµ·
    0.06
    tem
    0.06
    eware
    0.06
    Activations Density 0.004%

    No Known Activations