© 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. 20094
    Prev
    Next
    INDEX
    Explanations

    really?

    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
    çľ¼éĩĮ
    -0.06
    oot
    -0.05
    ced
    -0.05
    æĪª
    -0.05
    nek
    -0.05
    å°¾
    -0.05
    út
    -0.05
    ciÄħż
    -0.05
    /rest
    -0.05
    ä¸Ģçľ¼
    -0.05
    POSITIVE LOGITS
    arking
    0.06
    iany
    0.06
    并ä¸Ķåľ¨
    0.06
    irro
    0.05
     appréci
    0.05
     ÑĤомÑĥ
    0.05
    áĥĶáĥĹ
    0.05
    åĬŁåĬĽ
    0.05
    otent
    0.05
    agements
    0.05
    Activations Density 0.002%

    No Known Activations