© 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. 21575
    Prev
    Next
    INDEX
    Explanations

    STATES OF AMERICA

    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
    èĻ½çĦ¶æĺ¯
    -0.05
     Perr
    -0.05
    ä½ĵç³»åĴĮ
    -0.05
    ä½ĵç³»ä¸Ń
    -0.05
    积æŀģ主åĬ¨
    -0.05
     positive
    -0.05
    K
    -0.05
     K
    -0.05
    om
    -0.05
    ç¼ĸ
    -0.05
    POSITIVE LOGITS
    odka
    0.06
    estens
    0.06
     모ë¦Ħ
    0.06
     drog
    0.06
    vÃŃo
    0.06
    leased
    0.06
     vali
    0.06
    siasi
    0.06
    towe
    0.06
    ruc
    0.06
    Activations Density 0.001%

    No Known Activations