© 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. 19832
    Prev
    Next
    INDEX
    Explanations

    medical jargon and dates

    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
    пода
    -0.06
     пода
    -0.06
    jah
    -0.06
    大èĴľ
    -0.06
    åĨĻä¸Ģç¯ĩ
    -0.06
    大éĥ¨
    -0.05
     confron
    -0.05
    inum
    -0.05
    çį¨
    -0.05
    neh
    -0.05
    POSITIVE LOGITS
    寺
    0.06
     Estes
    0.05
    ؤÙĩا
    0.05
    ieux
    0.05
    æľĿ
    0.05
    æķħæѤ
    0.05
    æķ£
    0.05
    brook
    0.05
    ason
    0.05
    ZX
    0.05
    Activations Density 0.003%

    No Known Activations