© 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. 16743
    Prev
    Next
    INDEX
    Explanations

    funny things

    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
    igma
    -0.06
    etic
    -0.06
    ige
    -0.05
     Diante
    -0.05
    åıĸ
    -0.05
    太
    -0.05
    ated
    -0.05
     Afinal
    -0.05
    åŃ½
    -0.05
    ît
    -0.05
    POSITIVE LOGITS
    ént
    0.06
    umentos
    0.06
    /animate
    0.06
    jder
    0.06
    人æĦı
    0.06
    AHAN
    0.06
     previously
    0.06
    bÃŃ
    0.06
     presti
    0.06
    yno
    0.06
    Activations Density 0.003%

    No Known Activations