© 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. 20544
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    så
    -0.06
    grap
    -0.06
    æľīä¸įåIJĮçļĦ
    -0.06
     roup
    -0.06
    Í
    -0.05
    tä
    -0.05
    europ
    -0.05
    ç»Ī
    -0.05
    åĬ¡
    -0.05
     dem
    -0.05
    POSITIVE LOGITS
    etter
    0.06
    رÙĥاÙĨ
    0.06
    oire
    0.06
     صØŃØ©
    0.06
    ÙĪÙĤØ©
    0.05
    -page
    0.05
     ấn
    0.05
    urie
    0.05
    itter
    0.05
    åĦ¿çļĦ
    0.05
    Activations Density 0.005%

    No Known Activations