© 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. 19246
    Prev
    Next
    INDEX
    Explanations

    permission to use and copy

    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
    ais
    -0.06
     pala
    -0.06
    agos
    -0.06
    ยà¹Į
    -0.06
     succesfully
    -0.06
    atalog
    -0.05
    éľŀ
    -0.05
    aign
    -0.05
    æĿIJ
    -0.05
    æĹłéĿŀ
    -0.05
    POSITIVE LOGITS
    usp
    0.05
     script
    0.05
    ên
    0.05
    ordes
    0.05
    æīĢåľ¨
    0.05
    ä¸Ģå¿ĥ
    0.05
     veget
    0.05
    æĺı
    0.05
    +":
    0.05
    Å¡nj
    0.05
    Activations Density 0.152%

    No Known Activations