© 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. 20417
    Prev
    Next
    INDEX
    Explanations

    data and code constructs

    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
    人家
    -0.06
    APA
    -0.05
     agility
    -0.05
    è¿Ľåıĸ
    -0.05
    çģµæ´»
    -0.05
    åĪ°æľī
    -0.05
    ä¸ĢæĿ¥
    -0.05
    icke
    -0.05
    åĪ°è¿Ļ
    -0.05
     indeed
    -0.05
    POSITIVE LOGITS
     Seluruh
    0.06
    etin
    0.06
    oir
    0.06
    度ãĤĤ
    0.05
    nius
    0.05
    boy
    0.05
    ÛĮرÙĩ
    0.05
    chau
    0.05
    برت
    0.05
    度çļĦ
    0.05
    Activations Density 0.003%

    No Known Activations