© 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. 22565
    Prev
    Next
    INDEX
    Explanations

    military offensive attack invasion operation

    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
     tut
    -0.06
    é£İ鼨
    -0.06
    å³Ļ
    -0.06
    xid
    -0.05
    åĽĽæµ·
    -0.05
    åħ±åŃĺ
    -0.05
     intermedi
    -0.05
    åħģ
    -0.05
    inez
    -0.05
    åIJĮ
    -0.05
    POSITIVE LOGITS
    解åĨ»
    0.06
    emas
    0.06
    obile
    0.06
     Grandes
    0.06
     viá»ĩn
    0.06
     ساÙħسÙĪÙĨ
    0.06
    ä¸ĵåĪ©æĬĢæľ¯
    0.06
     flaw
    0.06
    ampi
    0.06
    è£ħ饰设计
    0.06
    Activations Density 0.027%

    No Known Activations