© 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. 17502
    Prev
    Next
    INDEX
    Explanations

    citations] or references)

    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
    åĪ©
    -0.05
    vorg
    -0.05
    æľīåĪ©
    -0.05
     gelen
    -0.05
    iesen
    -0.05
    หมาย
    -0.05
    å¥Ķ
    -0.05
    å¤ļéĩį
    -0.05
    èģĺ
    -0.05
    Trou
    -0.05
    POSITIVE LOGITS
    ä¸Ģå®ļæľĥ
    0.06
    number
    0.06
    igel
    0.06
     number
    0.05
    uid
    0.05
    uela
    0.05
    odor
    0.05
    ä¸Ģå®ļä¼ļ
    0.05
    详ç»Ĩæııè¿°
    0.05
    uta
    0.05
    Activations Density 0.033%

    No Known Activations