© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19710
    Prev
    Next
    INDEX
    Explanations

    special characters or codes

    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
    inge
    -0.06
    rous
    -0.06
    getting
    -0.06
    ç±»çŃī
    -0.05
    æ´»åĬ¨çŃī
    -0.05
    /></
    -0.05
    eds
    -0.05
    cha
    -0.05
    LN
    -0.05
    åįıä¼ļä¼ļåijĺ
    -0.05
    POSITIVE LOGITS
    ubil
    0.06
    ambar
    0.06
    ä¸į
    0.06
     ÙĨÙģر
    0.06
    ạch
    0.06
    -columns
    0.06
    okol
    0.06
     routi
    0.06
    ä¸įèĭŁ
    0.06
    ovol
    0.05
    Activations Density 0.001%

    No Known Activations