© 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. 21251
    Prev
    Next
    INDEX
    Explanations

    present invention, American Society

    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
    erry
    -0.05
    æĬĹ
    -0.05
     Brit
    -0.05
     عاÙĦ
    -0.05
    edly
    -0.05
     conlle
    -0.05
    åı¤ä»Ĭ
    -0.05
     непÑĢо
    -0.05
    æ²Ļæ²³
    -0.05
    unner
    -0.05
    POSITIVE LOGITS
    mong
    0.07
    ako
    0.07
     former
    0.06
    éłĤãģijãģ¾ãģĻ
    0.06
    åĢĴæķ°
    0.06
    Ùħا
    0.06
    ój
    0.06
     mong
    0.05
    åĢĴ
    0.05
    家ä¼Ļ
    0.05
    Activations Density 0.003%

    No Known Activations