© 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. 20139
    Prev
    Next
    INDEX
    Explanations

    Jayle, Ruth, Walter, Lyle

    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
    æĸ°åĬłåĿ¡
    -0.06
    isteren
    -0.06
     rett
    -0.06
     explicou
    -0.05
     naf
    -0.05
    ãģ¨è¨Ģãģ£ãģ¦
    -0.05
    çļĦäºĭåĦ¿
    -0.05
    aranya
    -0.05
    æĿ¥æºIJäºİ
    -0.05
    ffe
    -0.05
    POSITIVE LOGITS
    Ñij
    0.05
    ason
    0.05
    åģļåĩºäºĨ
    0.05
    çĭ¬
    0.05
    æľį
    0.05
    å§IJ
    0.05
     uncle
    0.05
    prima
    0.05
     afford
    0.05
     Lady
    0.05
    Activations Density 0.365%

    No Known Activations