© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18242
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ncer
    -0.06
    ourg
    -0.06
     equipa
    -0.06
    åĽ¢éĺŁçļĦ
    -0.06
    quip
    -0.05
    дай
    -0.05
     Asturias
    -0.05
    _known
    -0.05
    æľªçŁ¥çļĦ
    -0.05
     Kamp
    -0.05
    POSITIVE LOGITS
    ++;
    0.05
    èĭijå°ıåĮº
    0.05
     afer
    0.05
     continued
    0.05
    æŀĿèĬ±
    0.05
    ile
    0.05
     Rel
    0.05
     consolidated
    0.05
    MAC
    0.05
    .c
    0.05
    Activations Density 0.029%

    No Known Activations