© 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. 19687
    Prev
    Next
    INDEX
    Explanations

    profession or occupation

    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
    hips
    -0.06
    phone
    -0.05
    вин
    -0.05
    åĪ°ä½į
    -0.05
    žel
    -0.05
     Cousins
    -0.05
    çļĦæĺ¯ä¸Ģ个
    -0.05
    ׳×Ļ×Ķ
    -0.05
    prech
    -0.05
    зни
    -0.05
    POSITIVE LOGITS
    ÑĤеÑĢÑı
    0.06
    etze
    0.06
    kÅĤ
    0.06
    ueil
    0.06
     resto
    0.05
    为å®ĺ
    0.05
     profession
    0.05
    尽头
    0.05
    ä»ĬçĶŁ
    0.05
     belang
    0.05
    Activations Density 0.009%

    No Known Activations