© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    ï¸ı
    -0.06
    ï¸İ
    -0.05
    -0.05
    iedi
    -0.05
     miro
    -0.05
    åIJĦ大
    -0.05
     cifra
    -0.05
     embl
    -0.05
    ä»»ä½ķåħ¶ä»ĸ
    -0.05
    æĬ½ç©º
    -0.05
    POSITIVE LOGITS
    ÑĮеÑĢа
    0.06
    "w
    0.06
    aksin
    0.06
    éder
    0.06
     "@"
    0.06
    enje
    0.06
     totiž
    0.06
    наÑĩа
    0.06
     Bronx
    0.06
    ื
    0.06
    Activations Density 0.114%

    No Known Activations