© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19504
    Prev
    Next
    INDEX
    Explanations

    each row, star, page, Method

    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
    chten
    -0.06
    躯
    -0.06
    Ｖ
    -0.06
    hrs
    -0.05
    miss
    -0.05
    chr
    -0.05
    rove
    -0.05
    лÑıÑĤ
    -0.05
    ,..
    -0.05
    ovo
    -0.05
    POSITIVE LOGITS
    ØŃاÙĦ
    0.06
    å¼Ĥä½į
    0.05
    osz
    0.05
    Wrap
    0.05
    atched
    0.05
     возб
    0.05
    .erb
    0.05
    Screenshot
    0.05
    åĿIJ
    0.05
     evid
    0.05
    Activations Density 0.031%

    No Known Activations