© 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. 21858
    Prev
    Next
    INDEX
    Explanations

    shocked, hello, sought, understand, ycling, iac

    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
    erede
    -0.05
    ivable
    -0.05
    има
    -0.05
    porque
    -0.05
    éĢļ常æĺ¯
    -0.05
    ç»ĻäºĨ
    -0.05
    æĿŁ
    -0.05
    éĻħ
    -0.05
    æĺĻ
    -0.05
    缴æİ¥ä»İ
    -0.05
    POSITIVE LOGITS
    kÃŃv
    0.06
     barb
    0.05
    享åıĹçĶŁæ´»
    0.05
    对å¤ĸå¼ĢæĶ¾
    0.05
    Ùĥب
    0.05
    slow
    0.05
    è¾±
    0.05
     morbido
    0.05
    ì©Į
    0.05
    ä»ĭæĦı
    0.05
    Activations Density 0.001%

    No Known Activations