© 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. 18706
    Prev
    Next
    INDEX
    Explanations

    summarize or review

    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
     err
    -0.06
    宣åijĬ
    -0.05
    æķ´
    -0.05
    ial
    -0.05
    кÑĥÑİ
    -0.05
    apult
    -0.05
    ousing
    -0.05
    sche
    -0.05
    sas
    -0.05
    ť
    -0.05
    POSITIVE LOGITS
     odm
    0.06
    nTo
    0.06
    ä»Ļåı°
    0.06
    skirts
    0.06
    é¸¡æ¯Ľ
    0.06
     caden
    0.06
    antai
    0.06
    екÑģи
    0.06
     infi
    0.06
     cadr
    0.06
    Activations Density 0.001%

    No Known Activations