© 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. 18243
    Prev
    Next
    INDEX
    Explanations

    text style

    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
    æĥħ
    -0.05
    hofer
    -0.05
    å¤įåİŁ
    -0.05
    ÑĮеÑĢ
    -0.05
    oto
    -0.05
     sn
    -0.05
    elan
    -0.05
     Wo
    -0.05
    iele
    -0.05
    AVA
    -0.05
    POSITIVE LOGITS
    ekor
    0.07
    adak
    0.07
    -bearing
    0.07
    åľ¨è¿Ļåľº
    0.06
    icar
    0.06
    åĵ½
    0.06
    fontsize
    0.06
    èıľé¸Ł
    0.06
    å´½
    0.06
    åı¯ä»¥æł¹æį®èĩªå·±çļĦ
    0.06
    Activations Density 0.024%

    No Known Activations