© 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. 18745
    Prev
    Next
    INDEX
    Explanations

    urocutaneous, gonquin

    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
    åĴĮæĶ¹åĸĦ
    -0.06
    oster
    -0.06
    ROSS
    -0.06
    ietÃł
    -0.06
    alde
    -0.06
    обÑĢазование
    -0.06
     palav
    -0.06
    privation
    -0.06
    åĴĮå¤ĦçIJĨ
    -0.06
    æĻ®æ£®
    -0.06
    POSITIVE LOGITS
    whose
    0.06
     whose
    0.06
    踪影
    0.05
    ä»Ĩ
    0.05
     fl
    0.05
    ajn
    0.05
    otal
    0.05
    缩
    0.05
    inem
    0.04
    å°±ä¸įçĶ¨
    0.04
    Activations Density 0.018%

    No Known Activations