© 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. 19486
    Prev
    Next
    INDEX
    Explanations

    stopping, arriving, or parking

    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
    egen
    -0.06
    ลาม
    -0.06
     dynamics
    -0.06
    è´¯éĢļ
    -0.05
    京津
    -0.05
    串èģĶ
    -0.05
    åij¨å²ģ以ä¸ĭ
    -0.05
    æĭī
    -0.05
    串è¡Į
    -0.05
    ìĬ¹
    -0.05
    POSITIVE LOGITS
    è´´è¿ij
    0.06
    hoff
    0.06
    æĤ£èĢħåľ¨
    0.06
    ibilit
    0.06
    utat
    0.06
     stad
    0.06
    è¿ijæĪĺ
    0.05
     zi
    0.05
    çī¹
    0.05
    kring
    0.05
    Activations Density 0.035%

    No Known Activations