© 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. 16632
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     either
    -0.07
    garan
    -0.06
    Ñĭ
    -0.05
    梦éĩĮ
    -0.05
    ilities
    -0.05
    either
    -0.05
    ility
    -0.05
    kos
    -0.05
    eny
    -0.05
    arif
    -0.05
    POSITIVE LOGITS
    à¸ģัà¸Ļà¹Ħà¸Ľ
    0.06
    ijske
    0.06
    ziÄĻki
    0.05
    prav
    0.05
    appable
    0.05
     fed
    0.05
    اÙĩدة
    0.05
    åĴª
    0.05
    å»
    0.05
    ısından
    0.05
    Activations Density 0.008%

    No Known Activations