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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19481
    Prev
    Next
    INDEX
    Explanations

    travel destinations

    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
    zeitig
    -0.07
    iché
    -0.06
    ed
    -0.06
    -Semitism
    -0.06
    frist
    -0.06
    é¢ĺæĦı
    -0.06
    ilÃł
    -0.06
    ими
    -0.06
    itud
    -0.06
    edly
    -0.06
    POSITIVE LOGITS
    erator
    0.07
    ymp
    0.07
    entiful
    0.07
    eer
    0.06
    alling
    0.06
    تابعة
    0.06
    iaires
    0.06
    วà¹Į
    0.06
     tamp
    0.06
    aiss
    0.06
    Activations Density 0.006%

    No Known Activations