© 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. 16759
    Prev
    Next
    INDEX
    Explanations

    llama, motorcycle, alien, cave, pants

    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
    engi
    -0.06
    "value
    -0.06
    isiaj
    -0.06
    åħ±åIJĮ为
    -0.06
    ipur
    -0.06
    enko
    -0.06
     Term
    -0.06
     semelh
    -0.06
    entiful
    -0.06
    èIJ¥åķĨ
    -0.06
    POSITIVE LOGITS
    å§ĵ
    0.06
    ÄĻd
    0.05
     parted
    0.05
    é¦ĸåıij
    0.05
    æĮij
    0.05
    åıĻ
    0.05
    -kind
    0.05
     تÙĩ
    0.05
    çļĦéĥ¨åĪĨ
    0.05
    Private
    0.05
    Activations Density 0.083%

    No Known Activations