© 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. 22489
    Prev
    Next
    INDEX
    Explanations

    energy policy and past initiatives

    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
    gro
    -0.05
    est
    -0.05
    iest
    -0.05
    estr
    -0.05
    ç´ł
    -0.05
    æĪı
    -0.05
    ios
    -0.05
    å®ĺæĸ¹
    -0.05
    aget
    -0.05
    oku
    -0.05
    POSITIVE LOGITS
     zp
    0.06
     saura
    0.06
    äºĨçĤ¹
    0.06
     ÑģÑģÑĭлки
    0.06
    èµ°ä¸Ģèµ°
    0.06
    angelo
    0.05
    第äºĮæī¹
    0.05
    æ±ķ
    0.05
     devrez
    0.05
    è¿Ļ个åĵģçīĮ
    0.05
    Activations Density 0.007%

    No Known Activations