© 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. 16572
    Prev
    Next
    INDEX
    Explanations

    animal species

    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
     repmat
    -0.07
    acto
    -0.07
    voz
    -0.06
    ä½łçļĦåIJįåŃĹ
    -0.06
    apse
    -0.06
    å°Ĩå°±
    -0.06
    ç¥ŀä¹ĭ
    -0.06
    å¼¥
    -0.06
    pets
    -0.06
    tvr
    -0.06
    POSITIVE LOGITS
    éģ©
    0.05
     chân
    0.05
    æĻļ
    0.05
    èĮ¶
    0.05
    åıĻ
    0.05
    бал
    0.05
    buscar
    0.05
    éħĮ
    0.05
    å°ı
    0.05
    åģ·
    0.05
    Activations Density 0.002%

    No Known Activations