© 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. 18605
    Prev
    Next
    INDEX
    Explanations

    educational qualifications

    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
    terna
    -0.06
    jaa
    -0.06
    åĽŀæĹĭ
    -0.06
    ViewById
    -0.05
    idane
    -0.05
    olong
    -0.05
    æŃ£å¼ı
    -0.05
    flu
    -0.05
     GENERALE
    -0.05
    éter
    -0.05
    POSITIVE LOGITS
    ¿
    0.06
    sic
    0.05
    PECT
    0.05
    ror
    0.05
    ีà¹Īยว
    0.05
    ulus
    0.05
    iffe
    0.05
     ...
    0.05
    row
    0.05
     inquiries
    0.05
    Activations Density 0.011%

    No Known Activations