© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19452
    Prev
    Next
    INDEX
    Explanations

    installing software dependencies

    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
    æĿ¥æºIJäºİ
    -0.06
     mut
    -0.05
    _mut
    -0.05
    å¸ĥç½®
    -0.05
    alse
    -0.05
    æĿ¥èĩª
    -0.05
    pr
    -0.05
    .va
    -0.05
     did
    -0.05
    è¡Įäºĭ
    -0.05
    POSITIVE LOGITS
    ifikationen
    0.06
    chien
    0.06
    èı²çī¹
    0.06
    ifico
    0.06
    reven
    0.06
    ossi
    0.06
    æĬ¥è®°èĢħ
    0.06
    æľīæĦıåIJij
    0.06
    DEST
    0.06
    é«ĺ精度
    0.06
    Activations Density 0.008%

    No Known Activations