© 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. 19362
    Prev
    Next
    INDEX
    Explanations

    0 followed by punctuation

    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
    顾
    -0.06
    æĦıæĥ³
    -0.05
    éĿĴ
    -0.05
    ung
    -0.05
    è¿ij
    -0.05
    oya
    -0.05
     sonor
    -0.05
    åĪ»
    -0.05
    è¿ŀåIJĮ
    -0.05
    å¤ĩå¿ĺ
    -0.05
    POSITIVE LOGITS
    ibaba
    0.06
    upt
    0.06
    ллÑı
    0.06
     propre
    0.05
    ØŃÙħ
    0.05
    itär
    0.05
    ãģ®éļĽãģ¯
    0.05
    åľ¨ç¬¬
    0.05
    }"
    0.05
     Revenge
    0.05
    Activations Density 0.012%

    No Known Activations