© 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. 16587
    Prev
    Next
    INDEX
    Explanations

    budget deficit fiscal responsibility

    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
    ivet
    -0.06
    iven
    -0.06
    ask
    -0.06
    iscos
    -0.05
    isco
    -0.05
     continental
    -0.05
     Gef
    -0.05
     mut
    -0.05
    çļĩåĨł
    -0.05
    å®Įç¾İä¸ĸçķĮ
    -0.05
    POSITIVE LOGITS
    æĶ¶æĶ¯
    0.08
    ÙĪاÙħ
    0.06
    赤åŃĹ
    0.06
    ehe
    0.06
     overd
    0.06
     ballo
    0.06
    gant
    0.06
     austerity
    0.06
    OOT
    0.06
     Load
    0.06
    Activations Density 0.035%

    No Known Activations