© 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. 22086
    Prev
    Next
    INDEX
    Explanations

    e.g

    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
    åĽ£
    -0.07
    åį«ä¸ľ
    -0.06
    olest
    -0.06
    itational
    -0.06
    åħ·æľīä¸Ģå®ļ
    -0.06
    大纲
    -0.06
     phong
    -0.06
    ائج
    -0.06
    è¯ķä¸Ģè¯ķ
    -0.06
    æľīä¸Ģå®ļ
    -0.06
    POSITIVE LOGITS
     par
    0.06
    ö
    0.06
    å©Ĩ
    0.05
     ost
    0.05
     sp
    0.05
     bel
    0.05
    俯
    0.05
     vers
    0.05
    é¢
    0.05
    оÑģÑĤ
    0.05
    Activations Density 0.001%

    No Known Activations