© 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. 20673
    Prev
    Next
    INDEX
    Explanations

    programming file extensions

    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
     Gleichzeitig
    -0.06
    è¿Ļ件
    -0.06
    alikan
    -0.06
     concurrently
    -0.05
     simultaneously
    -0.05
    è¿Ļä¸ªæľºä¼ļ
    -0.05
    è¿Ļ款产åĵģ
    -0.05
    åħ¶ä»ĸåľ°åĮº
    -0.05
    è¿ĻæĿ¡
    -0.05
     Firma
    -0.05
    POSITIVE LOGITS
    gev
    0.07
    æĮĩçļĦ
    0.07
    cole
    0.06
    çģ¶
    0.06
    ãĥªãĤª
    0.06
    ato
    0.06
    atak
    0.06
    æľªå¤®
    0.06
    estro
    0.05
    æľīåı²
    0.05
    Activations Density 0.005%

    No Known Activations