© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19314
    Prev
    Next
    INDEX
    Explanations

    asynchronous operations and calls

    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
    itarian
    -0.06
    голов
    -0.06
     zam
    -0.05
    ativa
    -0.05
    itele
    -0.05
    å
    -0.05
    isman
    -0.05
     comparaison
    -0.05
    å¾ĢæľŁç²¾å½©
    -0.05
    íĹĺ
    -0.05
    POSITIVE LOGITS
    idium
    0.06
    illes
    0.06
    西è¡Ĺ
    0.06
    åħ«è§Ĵ
    0.06
    iewicz
    0.06
    ODO
    0.06
     hẳn
    0.06
    èģĶæĴŃ
    0.06
     entirely
    0.06
    ivio
    0.06
    Activations Density 0.006%

    No Known Activations