© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21909
    Prev
    Next
    INDEX
    Explanations

    modular, large, visual, mobile, remote, healthcare, cognitive, communication, industrial

    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
    ny
    -0.06
    èĪį
    -0.06
    co
    -0.05
    оÑĤо
    -0.05
    ous
    -0.05
    符åIJĪ
    -0.05
    fe
    -0.05
    tection
    -0.05
    åķ
    -0.05
    oh
    -0.05
    POSITIVE LOGITS
    大头
    0.07
    ики
    0.06
    venz
    0.06
    亦æĪĸæĺ¯
    0.06
     takdir
    0.06
    缴è§ĤçļĦæĸ¹å¼ı
    0.06
    endom
    0.06
    erken
    0.06
    INDER
    0.06
    icides
    0.06
    Activations Density 0.042%

    No Known Activations