© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    chemical compound suffixes

    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
    ger
    -0.06
    itud
    -0.06
    èĢĮéĻį
    -0.06
    alon
    -0.05
    onta
    -0.05
    aced
    -0.05
    åıĪä¸Ģ个
    -0.05
    ç¿ĺ
    -0.05
    ×Ļר×ķ
    -0.05
    acious
    -0.05
    POSITIVE LOGITS
    ÙħÙĬز
    0.06
    级æĹħ游æĻ¯åĮº
    0.06
    ubu
    0.06
    oub
    0.05
     negó
    0.05
     kerto
    0.05
    åĿIJåľ¨
    0.05
    人çĶŁ
    0.05
    å§Ķ
    0.05
    åĭī
    0.05
    Activations Density 0.008%

    No Known Activations