© 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. 22524
    Prev
    Next
    INDEX
    Explanations

    generation and millennials

    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
    dynamic
    -0.06
    å¤įæĸ¹
    -0.06
    cea
    -0.06
     Branch
    -0.06
    burgh
    -0.06
    branches
    -0.05
    åĨ¬
    -0.05
    emb
    -0.05
    好æĸĩ
    -0.05
    ngthen
    -0.05
    POSITIVE LOGITS
    è¿Ļæī¹
    0.07
    ä¹ĭ交
    0.06
     mem
    0.06
     ges
    0.06
    Generation
    0.05
    çĹŀ
    0.05
     Generation
    0.05
    æī¹
    0.05
     dif
    0.05
     perce
    0.05
    Activations Density 0.033%

    No Known Activations