© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16724
    Prev
    Next
    INDEX
    Explanations

    prepare statements with parameters

    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
    Negative Logits
    clud
    -0.06
    åħľ
    -0.06
    çľĭä½ł
    -0.05
    pling
    -0.05
    æĭ¢
    -0.05
     another
    -0.05
    {{{
    -0.05
    area
    -0.05
    è¯Ŀ说
    -0.05
    ple
    -0.05
    POSITIVE LOGITS
    ARG
    0.06
    araf
    0.06
     corros
    0.06
    urier
    0.06
    еÑģÑĤво
    0.06
     recons
    0.06
    ë¥
    0.06
    à¤Ĥतà¥įर
    0.06
    åĮª
    0.06
    icama
    0.06
    Activations Density 0.005%

    No Known Activations